TILens Daily Edition 2026-11-04 Filters: github=included Stats: 483 articles, 30 sources, 51 releases, 395 research papers Top topics: AI, AI Research, AI Tools ## News - Tool calling for small on-device LLMs that don't support tool calling Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/dannickstark/tool-calling-for-small-on-device-llms-that-dont-support-tool-calling-2dh7 - A heartbeat that goes quiet when the route is dead: signed presence records with a short TTL Source: devto-javascript Topic: JavaScript URL: https://dev.to/ashwar_sadh_f7abe6f82c8e9/a-heartbeat-that-goes-quiet-when-the-route-is-dead-signed-presence-records-with-a-short-ttl-26e8 - How to Programmatically Convert HEIC to PNG in Web Applications Source: devto-javascript Topic: JavaScript URL: https://dev.to/robertethreet/how-to-programmatically-convert-heic-to-png-in-web-applications-41lc - getCurrentPosition() Has No Default Timeout. That's the Trap. Source: devto-javascript Topic: JavaScript URL: https://dev.to/parsajiravand/getcurrentposition-has-no-default-timeout-thats-the-trap-3h5p - Kubernetes CPU Limits and JVM Throttling: Why p99 Spikes With Plenty of Idle CPU Source: java-code-geeks Topic: Java URL: https://www.javacodegeeks.com/2026/11/kubernetes-cpu-limits-and-jvm-throttling-why-p99-spikes-with-plenty-of-idle-cpu.html - TypeScript `globalThis` Typing in 2026: Safely Adding Properties to the Global Scope Without `any` Source: devto-javascript Topic: JavaScript URL: https://dev.to/jsmanifest/typescript-globalthis-typing-in-2026-safely-adding-properties-to-the-global-scope-without-any-3cm9 - As LLMs Devour the Storage Market, Fujifilm Bets on Tape Source: hackaday Topic: Hardware (+AI) URL: https://hackaday.com/2026/11/03/as-llms-devour-the-storage-market-fujifilm-bets-on-tape/ - How to Become a Front-End Developer: A Simple Beginner Roadmap Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/kushkrg/how-to-become-a-front-end-developer-a-simple-beginner-roadmap-4phg - Building a Neon City Map in PixiJS: Layers, Fog and Traffic Source: devto-javascript Topic: JavaScript URL: https://dev.to/denshin/building-a-neon-city-map-in-pixijs-layers-fog-and-traffic-d4c - I built a free checker for non-US founders with a US LLC (Form 5472) Source: devto-javascript Topic: JavaScript URL: https://dev.to/shubh_1a7a40ad162c0848/i-built-a-free-checker-for-non-us-founders-with-a-us-llc-form-5472-13no - Why Your Google Maps Rank Changes Block by Block (and How to Model It in JavaScript) Source: devto-javascript Topic: JavaScript URL: https://dev.to/gmbranker7759_2600ddf7348/why-your-google-maps-rank-changes-block-by-block-and-how-to-model-it-in-javascript-dec - Building an MBTI Cognitive Functions Test in JavaScript: Data Model and Scoring Source: devto-javascript Topic: JavaScript URL: https://dev.to/nicovarga/building-an-mbti-cognitive-functions-test-in-javascript-data-model-and-scoring-30e3 - A college notice board in React: a first project for web design students Source: devto-javascript Topic: JavaScript (+React) URL: https://dev.to/dzimark/a-college-notice-board-in-react-a-firsreactbeginnerswebdevjavascriptt-project-for-web-design-3ci9 - Where Does Your Data Go? The Route Map, Redirects and Browser Storage of app.onepassapps.com Source: devto-javascript Topic: JavaScript URL: https://dev.to/onepassapps/where-does-your-data-go-the-route-map-redirects-and-browser-storage-of-apponepassappscom-15be - OpenAI Faced Years of Security Warnings. Why Is It Hiring Outside Hackers Now? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-security-warnings-outside-hackers/ - India’s EloElo nabs $80M from NBCUniversal to bet on the country’s rising microdrama market Source: techcrunch Topic: General URL: https://techcrunch.com/2026/11/03/indias-eloelo-nabs-80m-from-nbc-universal-to-bet-on-the-countrys-rising-microdrama-market/ - Everything That Happened in AI Today (Wednesday, November 4, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-november-4-2026/ - AMD on track to overtake Intel as biggest x86 outfit Source: theregister Topic: General URL: https://www.theregister.com/systems/2026/11/04/amd-on-track-to-overtake-intel-as-biggest-x86-outfit/5307448 - Cat Feeder Ensures Fed Cats Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/11/03/cat-feeder-ensures-fed-cats/ - Philippine Migrant Worker Data Likely Leaked in 69GB Government Breach Source: darkreading Topic: DevSec URL: https://www.darkreading.com/cyberattacks-data-breaches/philippine-migrant-worker-data-69gb-government-breach - Driving the OnePassApps Studios With a Keyboard: Tab Order, Live Regions and Focus Rings Source: devto-javascript Topic: JavaScript URL: https://dev.to/onepassapps/driving-the-onepassapps-studios-with-a-keyboard-tab-order-live-regions-and-focus-rings-34f1 - Aussie Adobe assailant Canva announces layoffs in re-org affecting 22% of staff Source: theregister Topic: General URL: https://www.theregister.com/saas/2026/11/04/aussie-adobe-assailant-canva-announces-layoffs-in-re-org-affecting-22-of-staff/5307422 - Frost Flowers: a tap-to-plant puzzle built on a 1960s cellular automaton Source: devto-javascript Topic: JavaScript URL: https://dev.to/waitlab/frost-flowers-a-tap-to-plant-puzzle-built-on-a-1960s-cellular-automaton-415n - Etching Press Aims To Impress Source: hackaday Topic: Hardware URL: https://hackaday.com/2026/11/03/etching-press-aims-to-impress/ ## Releases - trunk/c5e48a5934f7f2037648389d04eaefc565ccfd96: Update torch-xpu-ops commit pin (#201788) Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2Fc5e48a5934f7f2037648389d04eaefc565ccfd96 - b12099 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12099 - trunk/8126db39a94175b16652502e0acd4637089c4b76 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F8126db39a94175b16652502e0acd4637089c4b76 - trunk/16b9d0a1b995ff954cc33ceb518ff3b43266a742: Size linalg.lstsq infos by the broadcast batch (#203043) Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F16b9d0a1b995ff954cc33ceb518ff3b43266a742 - b12098 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12098 - b12097 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12097 - b12096 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12096 - trunk/665ecdd5784fd7c8dfdf7dbb184fceb2b31c387f Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F665ecdd5784fd7c8dfdf7dbb184fceb2b31c387f - b12094 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12094 - v3.45.0 Source: gh-openai-python Topic: Python (+AI) URL: https://github.com/openai/openai-python/releases/tag/v3.45.0 - 2.1.8 Source: gh-sqlalchemy Topic: Python (+Databases) URL: https://github.com/sqlalchemy/sqlalchemy/releases/tag/rel_2_1_8 - Ray-2.60.0 Source: gh-ray Topic: AI URL: https://github.com/ray-project/ray/releases/tag/ray-2.60.0 - b12091 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12091 - trunk/8f9ae67022fe1965aa527634587bc150052b2265 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F8f9ae67022fe1965aa527634587bc150052b2265 - Model Catalog Source: gh-mlflow Topic: AI (+AI Tools) URL: https://github.com/mlflow/mlflow/releases/tag/model-catalog%2Flatest - 2.0.57 Source: gh-sqlalchemy Topic: Python (+Databases) URL: https://github.com/sqlalchemy/sqlalchemy/releases/tag/rel_2_0_57 - trunk/2e10e9e8998bf3d420dac3530dfff53bf784c880: [XPU][UT]fix test_effn_attn_uniform_zero_bias on XPU (#197543) Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F2e10e9e8998bf3d420dac3530dfff53bf784c880 - b12090 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12090 - b12089 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12089 - trunk/dadc7bdebb36d1d0b77793d2c9ea13bef725b5b8 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2Fdadc7bdebb36d1d0b77793d2c9ea13bef725b5b8 - trunk/d6db56f599beb3a4cd0a0430849af01021880d42 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2Fd6db56f599beb3a4cd0a0430849af01021880d42 - viable/strict/1793773755 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/viable%2Fstrict%2F1793773755 - nightly Source: gh-rust-analyzer Topic: Rust URL: https://github.com/rust-lang/rust-analyzer/releases/tag/nightly - b12087 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12087 - ciflow/trunk/203241: [UPDATE] Update Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203241 - ciflow/trunk/203150: [UPDATE] Update Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203150 - ciflow/trunk/203153: [UPDATE] Update Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203153 - ciflow/trunk/203152: [UPDATE] Update Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203152 - ciflow/trunk/203151: [UPDATE] Update Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203151 - trunk/9fb10c5e6567142b1c4b42f16b773e709170b5a6: Revert "[fix] `binary_cross_entropy_with_logits` gradients (#202129)" Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/trunk%2F9fb10c5e6567142b1c4b42f16b773e709170b5a6 - ciflow/trunk/203135 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203135 - ciflow/trunk/203134 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203134 - ciflow/trunk/203299 Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F203299 - b12086 Source: gh-llama-cpp Topic: AI (+AI Tools) URL: https://github.com/ggml-org/llama.cpp/releases/tag/b12086 - langchain-typesafe==0.0.1 Source: gh-langchain Topic: AI Tools (+AI) URL: https://github.com/langchain-ai/langchain/releases/tag/langchain-typesafe%3D%3D0.0.1 - ciflow/trunk/202678: [ROCm] Reuse a per-stream handle only on the stream it ran on (#202678) Source: gh-pytorch Topic: AI Tools (+AI) URL: https://github.com/pytorch/pytorch/releases/tag/ciflow%2Ftrunk%2F202678 - MongoDB Go Driver 2.9.3 Source: gh-mongo-go-driver Topic: MongoDB URL: https://github.com/mongodb/mongo-go-driver/releases/tag/v2.9.3 - v1.14.0.dev16 Source: gh-langflow Topic: AI (+AI Tools) URL: https://github.com/langflow-ai/langflow/releases/tag/v1.14.0.dev16 - 🚀 AutoGPT Platform v0.11.0 Source: gh-autogpt Topic: AI (+AI Tools) URL: https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.11.0 - Preview seed fixture (rolling) Source: gh-autogpt Topic: AI (+AI Tools, PostgreSQL) URL: https://github.com/Significant-Gravitas/AutoGPT/releases/tag/preview-seed-fixture - openclaw 2026.11.5-beta.1 Source: gh-openclaw Topic: AI (+AI Tools, PostgreSQL) URL: https://github.com/openclaw/openclaw/releases/tag/v2026.11.5-beta.1 - compound-engineering: v3.35.1 Source: gh-cep Topic: AI (+AI Tools) URL: https://github.com/EveryInc/compound-engineering-plugin/releases/tag/compound-engineering-v3.35.1 - 1.13.1 Source: gh-langflow Topic: AI (+AI Tools, PostgreSQL) URL: https://github.com/langflow-ai/langflow/releases/tag/v1.13.1 - 0.168.0-alpha.1 Source: gh-openai-codex Topic: AI (+AI Tools) URL: https://github.com/openai/codex/releases/tag/rust-v0.168.0-alpha.1 - release-publish/ed1bb7298985-1793760875 Source: gh-openclaw Topic: AI (+AI Tools) URL: https://github.com/openclaw/openclaw/releases/tag/release-publish%2Fed1bb7298985-1793760875 - release-publish/9a3ae43f5602-1793756853: fix(ui): localize skill and plugin feedback (#192305) Source: gh-openclaw Topic: AI (+AI Tools) URL: https://github.com/openclaw/openclaw/releases/tag/release-publish%2F9a3ae43f5602-1793756853 - 1.12.9 Source: gh-langflow Topic: AI (+AI Tools) URL: https://github.com/langflow-ai/langflow/releases/tag/v1.12.9 - Release v0.67.0-nightly.20261104.g89e9d25d6 Source: gh-gemini-cli Topic: AI (+AI Tools) URL: https://github.com/google-gemini/gemini-cli/releases/tag/v0.67.0-nightly.20261104.g89e9d25d6 - v0.44.0 Source: gh-comfyui Topic: AI (+AI Tools) URL: https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.44.0 - rust-v0.167.0-alpha.5 Source: gh-openai-codex Topic: AI (+AI Tools) URL: https://github.com/openai/codex/releases/tag/rust-v0.167.0-alpha.5 - v1.14.0.dev15 Source: gh-langflow Topic: AI (+AI Tools) URL: https://github.com/langflow-ai/langflow/releases/tag/v1.14.0.dev15 ## Research - Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2303.12212 - Variable Parameter Analysis for Scheduling One Machine Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2211.02107 - Loop unrolling of UCA models: distance labeling Source: arxiv-cs-ds Topic: Algorithms URL: https://arxiv.org/abs/2202.10527 - Bounded Discrete Bridges Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2506.02982 - Connected Dominating Sets in Triangulations Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2312.03399 - Kadison--Singer in Deterministic Polynomial Time Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.17266 - Max Independent Set Remains NP-hard when Excluding a Planar Induced Minor (and More) Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.11285 - Constant-factor approximation of MinCostCSP with a conservative majority polymorphism Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2607.10667 - Counterexamples to the Strong Roberson Conjecture Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2610.03550 - Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorithms Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2608.01320 - Complexity of conjunctive regular path query homomorphisms Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2305.07271 - Online Beck--Fiala Down to Logarithmic Sparsity Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2607.14238 - A Spectral Local-to-Global Principle for Spin Systems on Graphs with Girth At Least Five Source: arxiv-cs-dm Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2608.25491 - On the Power of Determinism in Multi-Item Auctions Source: arxiv-cs-dm Topic: Algorithms URL: https://arxiv.org/abs/2609.35711 - Detecting Historical Turning Points in Italian Media: A Complex Systems Approach to a Diachronic News Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14348 - RAP: Research Attention Prediction in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10092 - EvoOntology: A Self-Evolving Ontology Layer for Data Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15779 - Characterizing When Language Models Take Harmful Actions to Protect Their Assigned Goals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03374 - Language Models Learn to Improve Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23344 - Cross-Prompt Reuse of Entity-Replacement Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00352 - SWE-Opt: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25530 - Better Answers, Weaker Evidence Control: Evidence Bypass in On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01967 - ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00638 - EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18489 - MemRole: From Memories to Decisions for Long-Horizon Reasoning in Role-Playing Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01778 - FOLLIE: Automated Reasoning over the First Dataset of Sentences with their First-Order Logical Representation for French Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02129 - Tune the Baseline First: Most of Muon's Scaled Weight Decay Gain Is a Tuning Gap, but Its Small Real Advantage Grows With Model Size Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02529 - One Waveform, Two Stories: Benchmarking Speech-Acoustic Conflict in Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00325 - EffComp: Efficient Prompt Compression via Hybrid Reinforcement & Supervised Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02766 - Do Agents Still Follow the Rules? Benchmarking Rule Compliance under Agent Context Compaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03223 - Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06388 - ClickSight: An LLM Framework for Interpreting Student Clickstreams Through Learning Strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02021 - Window-Aware Scheduling for Health Messaging under Platform Delivery Constraints: Evidence from an AI-Powered WhatsApp Maternal and Infant Health Chatbot in Nigeria Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02834 - Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16656 - What Do LLM Judges Actually Verify? Matched Controls and Record Gaps for Document Currency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01311 - When frequency domain classification is superior to spatial Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00073 - IdeaTaste: Do LLMs Share the Research Taste of Human Researchers? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03424 - From Small to Large: Assessing Medical Reasoning, Benchmark Contamination, and Model Size in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00460 - Finitely Verifiable Segmentation: Decidability for Every Tokenizer with a Finite-State Verifier Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30168 - Rubric-Guided Process Reward for Stepwise Model Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29310 - Current state of LLMs for Arabic dialectal machine translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02271 - Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10266 - SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20431 - TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07688 - The Presupposition Problem in Representation Genesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21745 - WebHarbor: Docking Real Websites for Evolving GUI Agent Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03634 - Adaptive-Policy Distillation: Knowledge Injection under Information Asymmetry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00852 - Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03577 - D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03622 - How Green Is Your Manifesto? Scoring Environmental Positions in the 2024 EU Elections with an LLM Panel Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02033 - Quantiles, Not Points: Streaming Quantile Matching for Ordinal-Aware LLM-as-a-Judge Calibration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00447 - Sparse Autoencoder Attribution Graphs Are Decided at the Margin Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00606 - Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25421 - Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03317 - Spotting the Artificial: Dialogic Humor Improvisation in Humans and LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00492 - ConstraintMatch: Compositional Image-Text Matching through Constrained Regional Evidence Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00784 - Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22620 - Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11442 - Tmax: A simple recipe for terminal agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23321 - Circuit Oracle: Automating Attribution Graph Analysis via Natural-Language Queries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00420 - AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Question Answering over Scientific Citation Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34428 - Entity-Aware Evaluation of OCR Systems for Historical Document Transcription Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33004 - Contextual Linear Activation Steering of Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24693 - LegoEnv: Self-Evolving Agentic Environments via Modular Recombination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01834 - SYNC: A Training-Free Inference Controller for Dynamic Layer Selection in Multi-Persona Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02636 - Beyond Self-Reflection: An Execute-Distill-Verify Framework for Agentic Experience Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24428 - A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05165 - ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00819 - TopoSteer: Topological Layer Selection for Activation Steering in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01493 - When Rewards Depend on the Group, GRPO Plays a Tournament Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02404 - Wrong Together: Shared Bias in User Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01354 - NitiBench+: A Temporal Thai Legal Question Answering Benchmark Across 17 Domains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03576 - See, Think, Use: Diagnosing Perception and Reasoning Failures in VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01467 - Embedding Consistency Regulation for Persistent Semantic Routing in Compact Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00543 - Steering Readerly Dynamics: Trajectory-Guided Story Generation with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00469 - When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05414 - PlagiaCorpus: A Bilingual, Adversarial, and Cross-Lingual Dataset for Forensic Plagiarism Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02940 - Mitigating Bias in Automated Essay Scoring for ESL Learners via Contrastive Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16724 - EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22231 - External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11806 - Are Fake Citations a Form of Reward Hacking? A Pre-Registered Study of Post-Training and Citation Cues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01313 - Every Clause Counts: Instruction-Following Reranking by Multiplying Small, Answerable Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03179 - Information-Theoretic Design of Sparse Autoencoder-Based Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01378 - trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00038 - Automated grounding verification of AI statements about chest radiographs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09537 - Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02244 - HaloGuard 2.0: An Open-Weights Constitutional Output Guard for Multilingual Response Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02134 - GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02314 - User Attributes and Political Ideology Shape LLM Receptiveness in Online Political Debates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02908 - T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34103 - Bridging Static and Agentic RAG for Taiwanese Historical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23056 - EarlySelectKV: Anticipatory KV Selection via Cross-Layer Query Proxies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01715 - Specificity Bias and the Wikipedia Paradox: An xAI Analysis of AI Text Detectors under Domain Shift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03280 - Learning by Doing: Autonomously Compiling and Curating Agent Skills from Verified Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01386 - RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.04903 - Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.03113 - Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2606.02814 - Agentic Context Management for Multi-Turn Human-AI Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00518 - Rubric-Based Assessment of Student Reports Using Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01785 - Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27783 - MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01261 - SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07513 - Rethinking LLM Pruning via Test-Time Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01133 - Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15428 - LLMberjack: Guided Trimming of Debate Trees for Multi-Party Conversation Creation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04135 - ArSciKids: Arabic Curriculum-Aligned Datasets for Scientific Experiment and Multiple-Choice Question Generation in Primary Education Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01191 - Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03551 - Decentralized Multi-Agent Coordination and Communication in Shared Codebases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00314 - Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06600 - AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19847 - Decision Models as Policy Gates for Coding Agents: Explicit Policy Boundaries Improve Detection and Reduce False Alarms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02155 - FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01621 - Constructing Budgeted KGW Evasion through Token-Event Evidence Replacement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00726 - Diagnosing Model--Item Interactions in Language Model Benchmarks with LSIRM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02432 - Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41552 - Metamorphic Testing for Evaluating Robustness of Sentiment Analysis Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02248 - Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24965 - Maswao: An automatically collected, prepared, and benchmarked dataset for the South African Sign language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02903 - PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02540 - GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01143 - Multi-View Latent MoE: Letting Every Router Shape Expert Computation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40577 - Consilience for Verifier-Free Test-Time Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09898 - Item-Mean Surrogates: Why Richer Personas Fail to Deliver Individual Fidelity in LLMs as Human Surrogates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29455 - Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01733 - Queering the Audits: Community-Based Auditing of AI Harms to Queer Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00345 - A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37788 - VERS: Steering Reasoning Models by Editing Their Activation Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03040 - Distinguishing among reasoning levels of GPT 5.5 Pro via a grammar lens benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00555 - MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.07243 - MemShift: Separating Detection from Repair in LLM-Derived Personal Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02338 - Label Smoothing in Disguise? Gated Knowledge Distillation for Low-Resource Bangla Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01065 - When LLMs Modify Themselves: Convergence, Values, and Stopping in Iterative Self-Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01304 - Don't Guess, Ask Wisely: Benchmarking and Training Proactive Elicitation in Open-Domain LLM Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01878 - MEMENTO: Learning Context Management for Long Context Processing Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00244 - Hinted Scaling Laws Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02270 - A Survey on Agentic Security: Applications, Threats and Defenses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06445 - Concise-9B: Removing the Slack from a Reasoning Model's Thinking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02278 - Train the Sampler You Run: Few-Step Masked Diffusion Language Models via Mixture-Likelihood Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02666 - Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00215 - Does Random Search Discover Task Experts? Revisiting Neural Thickets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01262 - Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02985 - Poolwise: Evaluating Reward Models for Selection across Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31090 - EviCast: Forecasting Retrieval Gains Through Shared Response Calibration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02387 - Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02889 - LF-VideoQA: Evaluating Long-Video Understanding with Long-Form Theory-of-Mind Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00383 - AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00515 - Accounting for Irregular State Transitions through Belief Estimation in Online Medical Consultation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01474 - When 200 OK Is Not an Answer: Silent Fetch Failures in Agentic Web Content Acquisition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00884 - Creating Hybrid Interactive Narrative Systems with LLM: From Formal Description to Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02807 - ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02079 - Optimize the Harness, Not the Model: Fitting a Minimal Agent to a Self-Hostable LLM for Investigative Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03434 - Sentiment sensing: comparative analysis of multilingual sentiment dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01348 - TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01926 - ACTOR: Action-Centered Temporal Organization for Literary Role-Playing Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03184 - Action Verification through Conjecture and Refutation for Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02950 - MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02011 - A Token Is Not a Unit of Difficulty: Segmentation Controls Where Adaptive Computation Goes Inside a Word Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00983 - Unlocking Criminal Court Decisions: Flexible Information Extraction for Empirical Legal Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03051 - From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00078 - Text Corpora as Concept Fields: Providing Explainable Groundedness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05103 - ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03605 - MicroMouse: Masking Harmful Supervision in Long CoT via Relative Potential Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02710 - Theoretical Analysis of Byte-Pair Encoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.08671 - Scaling Makes It Possible: How Large Models Master Impossible Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02015 - Reinforcement World Model Learning for LLM-based Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05842 - MediaWiki Code2Code Search: Neural Retrieval for the Semantic Discovery of Open-Source Software Entities Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2607.26766 - When Does Adaptive Halting Win? Selection Rules Matter in Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02333 - Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18539 - Omni-Life: Benchmarking Omnimodal Real-Time AI Assistants in People's Daily Lives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02835 - A Multi-Instance LLM Framework for Rating the Quality of Surgical Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25440 - "I Wrote, I Paused, I Rewrote": A Mixed-Methods Study of Learner Perceptions of Process-Aware LLM Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00009 - From Lookups to Lessons: Turning Retrieved Knowledge into Parametric Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00450 - CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05849 - Finding Errors Is Not Enough: Selective Model Escalation for Entity-Targeted Sentiment Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02989 - Empathy Is Not the Scapegoat for Declines in Factuality and Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18541 - From Apparent Search Gains to Selection Failures: Auditing Test-Time Inference in Structured Workflow Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00579 - Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Driving QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00833 - Teach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00297 - Beyond Accuracy: How Quantization Affects Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02368 - CULTURE-CMT: Benchmarking Contextualized Social Media Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02018 - DuSE-Bench: Benchmarking Joint Reasoning over Evolving Dialogue and Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00755 - MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28397 - Edge-Optimized YOLOv11n Architecture for Offline Recognition of Nigerian Sign Language Alphanumeric Gestures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00025 - HistGramBench: Measuring Structural Recovery When Multimodal Models Redraw Historical Mathematical Diagrams as TikZ Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00081 - Stop Handcrafting Your Engine! GenDB-V: Towards AI-Generated and Formally Verified Database Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02779 - DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03142 - Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02017 - fog: Generating Expressive Motion through Layered Function Composition of Code for Heider-Simmel Animation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07952 - norregel: a preregistered benchmark of dated numeric values in Norwegian law Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29207 - A Systematic Analysis of Linguistic Features in AI-Generated English Text Detection Across Domains and Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04177 - HierSentNet: Hierarchical Sentiment Analysis Framework for Hate Speech Detection Using Binary and Multiclass Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.05819 - PredActBench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02372 - Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02319 - Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00883 - Beyond Outcome Rewards: Post-Rationale Distribution Optimization for Selective Prediction in Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38850 - Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37682 - Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01123 - Style over Substance? Linguistic Bias in LLM-based Peer Review Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35254 - BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01321 - HerHealthGPT: An Evidence-Grounded Conversational AI System for Women's Reproductive Health Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33931 - FlyWheel: Attention Kernels Built for the TPU Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01426 - Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02480 - Heirloom: Carrying a Phone's Personalization Across Base-Model Generations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00650 - SPARK: Self-Correcting Embodied Memory via Physical Re-Observation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00344 - XDecideBench: Evaluating Typed Decision Models and Confidence Policies Across Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01370 - Which Words a Model Fears: From a Refusal Direction to a Vocabulary-Wide Fear Lexicon Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02348 - ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.19144 - Detailed Derivation of The Backpropagation Algorithm Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02152 - The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01219 - When Should an Agent Refresh? Adaptive Index Reuse for Efficient Long-Horizon Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01429 - ViAdminShift: A Vietnamese Benchmark for Event-Level Knowledge Updates Built from the 2025 Administrative Reform Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03171 - Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14375 - Multi-Estimate Elicitation Does Not Uniformly Debias Language Model Judgments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00597 - UXBench: Benchmarking User Experience in AI Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09570 - MAC-Bench: Benchmarking Multi-Agent Collaboration via Interconnected Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01728 - Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01284 - Selective Linkage Precision for Released Medical Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02276 - Online Label-Free Gradient Matching for Continual Language Model Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03496 - Using OCR Heads to Verbalize Image Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18823 - Enhancing Language Model Reasoning with Structured Multi-Level Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00616 - VisCodeBench: a new benchmark dataset for Text-to-Vis reflecting real-world practice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02353 - Swap, Replicate, Read the Mass: A Protocol for Auditing Demographic Bias in System One Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00496 - Do media narratives shape foreign ownership? Evidence from African regions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.10239 - What Breaks and What Comes Back: Capability Damage and Recovery in Depth-Pruned Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00877 - From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00172 - VLMs Read Aloud: The Gap Between Recognizing and Using Visual Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01517 - Instruction-Tuned Models Locally Produce More Syntactic Overlap -- But Not More Conditional Reuse -- Than Humans Do Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26015 - Query Language Sensitivity in Automated Sentiment Scores of LLM Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13304 - EEG-HealthLLM: Hierarchical Adaptation of Large Language Models for Unified Heterogeneous EEG Health Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01652 - GAVAGAI: Referential Alignment for Infant-Scale Vision-Language Models via Balanced Optimal Transport Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00319 - TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02001 - What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00013 - Can Large Language Model Agents Learn by Watching Tutorial Videos? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01460 - Variable names provide priors: semantic grounding enables data-efficient numerical prediction by large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02637 - Can Large Language Models Extend Their Agentic Capabilities to Goal Pursuit in Open-Ended Multi-Turn Interaction? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01552 - Written Once, Read Differently How Language Models Own Answers Steer Their Next Ones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03198 - Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01496 - Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03377 - MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20191 - \textit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28213 - LLM-Enhanced Multimodal House Price Prediction using Structured, Textual, and Visual Features Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01615 - GatedV: Self-Gated Values for Transformer Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02145 - Humanized but Still True? Auditing Facts and Detection in AI-Text Humanizers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00359 - Steer, Don't Tell: Breaking Reasoning Plateaus with Reachability-Aligned Self-Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00796 - Write Facts the Way Models Read Them: Lifting the Two-Hop Curse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01519 - Skill++: Towards Lifelong Agents via Routing-Aware Skill Refinement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00544 - LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03308 - Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27462 - Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03526 - DR Pixel: Page-Native Deep Research with Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03097 - Representational Acquisition Under Bounded Resources Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21736 - Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01171 - Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00935 - Geometric and algebraic inference in humans and neural networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00387 - Ranked but Not Stopped: Detecting Prompt-Injection Hijacks from Typed Decision Models' Output Probabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02522 - Dual-Axis Policy Entailment: A Benchmark for Policy-Change Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00536 - Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01840 - Shared relations, specific choices: conditional sensitivity and competing pathways in language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01809 - Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00592 - Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23790 - Halal-NeSyNet: Clause-Scoped Neuro-Symbolic Cross-Attention for Automated Food Ingredient Auditing and Risk-Aware Halal Logistics Triage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01612 - FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02545 - Tracing How Language Models Integrate Temporal Anchors into Factual Recall Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01945 - Replay for LLM Continual Learning with Multi-Teacher On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02746 - SAGE (Subjectivity-Aware Generation Estimator): A Linguistic Framework for AI-Generated Review Detection * Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03060 - Unlearning by Extrapolating a Shrink-and-Heal Lookahead Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00374 - MafiaScope: Inspecting Multi-Agent Reasoning in Social Deduction Games Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10645 - One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19741 - When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11908 - A Capitulation Direction Emerges With Scale and Is Causally Load-Bearing Where Validation Is Strong: Eight Models, Two Families, and Five Measurement Hazards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02318 - Order-Only On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02112 - When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02273 - LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02332 - Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13217 - Uncertainty Quantification for LLM Function-Calling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22985 - GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02476 - They Know Where It Is, But Not What It Says: A Bilingual Hallucination Benchmark of Hadith Recall in Open LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02587 - A Bounded Evaluation Protocol for Representational Systematicity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01755 - Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01747 - Agent Skill Evaluation and Evolution: Frameworks and Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11435 - MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10616 - Robustness Starts with the Objective: Designing and Certifying Robust LLM-Generated Heuristics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00504 - VeriHarm-Bench: Measuring Harmful Success in LLM Coding Agents Verifiably Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03575 - Consolidating Reasoning with Test-Time Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02104 - InteractionBench: Measuring Timing, Task Accuracy, Whisper and Volume, and Grounding in Real-Time Voice Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02430 - Cross-Lingual Persona Effects in LLM Negotiation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00300 - Activation-Based Active Learning for In-Context Learning: Challenges and Insights Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05134 - Revisiting LLM Homogeneity Through a Multidimensional Lens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01549 - Test-Time Scaling for Open-Ended Reasoning at Small Model Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02208 - PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02791 - Outdated numeric values from Norwegian statutes and regulations in a further-trained model and its base model: a preregistered paired comparison of Borealis 2 and Gemma 4 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02334 - HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00986 - Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32955 - Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23811 - ICJ-Graph: A Citation Graph and a Layered Document Corpus of the International Court of Justice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02630 - The Scope Grammar of Natural-Language Rules: Counting and Enumerating Readings modulo Logical Equivalence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01825 - AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24387 - Strategist: Evolving Reasoning with Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03618 - VeriCypher: Named-Entity Verification for GraphRAG via Text-to-Cypher Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08274 - Hierarchy-Aware Multimodal Unlearning for Medical AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09867 - Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08210 - Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03092 - PsyInterviewee: Informational Invariance and Relational Adaptivity in Mental Health Interview Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41289 - Beyond fabrication: Misattributed numbers in papers written by AI research agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38691 - Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20436 - Interpreting Classical Readability Formulae as Surprisal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01359 - Reformulation and Equivalence of Bock's Algorithm for Exact Dependency Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00939 - When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08239 - Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01954 - SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasound Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02581 - TVP: TV is Almost All You Need for Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00588 - Dual Dimensionality for Local and Global Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18587 - DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04743 - Keepace.ai: A Technical Report on a Large Language Model for Sports and Health Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38249 - Constructing an Artworld Influencers Network by Mining Social Media Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02657 - S1CogBench: What System One Decision Models Can and Cannot Do on Cognitive Experiments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00911 - ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00011 - Meet Students Where They Are: Student-Prefix Teacher Adaptation for On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03133 - Do Multimodal Models Decide Consistently on Equivalent Optical Spectra? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00428 - As Expected? Efficient LLM Planning via Expectation-Observation Consistency Verification Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.02438 - CREDO: Evidence-Conditioned Credit Assignment for Temporal Reasoning Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01643 - VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03518 - Specification-Aware Predictive Uncertainty Decomposition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02956 - Can Large Language Models Capture Video Game Engagement? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.04379 - Subquadratic Attention with a Hierarchical Tree-Structured Indexer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42112 - CogRSI: Evolving and Auditing Cognitive Reasoning Strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01113 - Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21270 - Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02612 - Self-Refining Prompt Induction for Streaming Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00960 - MultiInpaintCOCO: Fine-Grained Visual Understanding in Multiple Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03309 - SelfImprove-Bench: Evaluating Generalization in Self-Improving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02797 - Multi-Turn Semantic Caching for Low-Cost LLM Serving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01077 - BanglishDepYT: Depression Detection in Native Bengali Social Media with Emotion-Preserving Preprocessing and Domain-Adaptive Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01633 - Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01320 - Latent Debate: A Surrogate Framework for Interpreting LLM Thinking towards Binary Decisions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01909 - Dh\={a}r\={a} Bench: An Evidence-Oriented Retrieval Benchmark for Indian Knowledge Systems Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.03196 - Audit at the Precision You Deploy: Quantization Reshapes a Subliminally Learned Preference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00665 - Li$^{2}$SAO: Lifting Light Single-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40726 - Multi-Agent Collusion and the J-Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02153 - Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38960 - LLMs Cannot Be Neutral: Gender Sensitivity Across Candidates, Evaluators, and Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02692 - CoworkOS:Scaling Agent Coworkers for Real-world Automation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03178 - Precedent Labels and Facts Shift LLM Approval Decisions in Opposite Directions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00672 - Who Should Score the Cache? Mid-Depth Layers Are the Best Judges of KV-Cache Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02230 - CompSkill: Compiling Execution Experience for Skill Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.01115 - Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22444 - Anthropogenic Regional Adaptation in Multimodal Vision-Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11490 - Parameter-Efficient Adaptation of Large Language Models to a Low-Resource Agglutinative Language: A Corpus, Datasets, and a Reproducible Benchmark for the Bashkir Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31397 - Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02740 - Latent Harness: Compiling Agent Behaviors into Post-Block Activation Shifts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01415 - Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29712 - ViSSFlow: Unifying Video-Conditioned Sound and Speech Generation via Joint Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24773 - The Structure of Disagreement in Emotion Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01539 - RAG-TRACE: Tracing Measurement Evidence and Diagnostic Completeness in AI-Generated ECG Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01409 - Conic Certification of Transformer Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00585 - ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24743 - Conditional Calibration Contracts under Coupled Load: A Branch-Aware Audit of Switched Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02121 - EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01268 - Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18549 - CuriousTogether: Implications of Curiosity and Cultural Grounding in Multi-Agent LLM Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01301 - Learning Timeline-Preserving Speech-to-Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00690 - Parsed Text Understates Vision-Language Models: From Below to Above Expert Agreement on Fine-Grained Facial Emotion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08162 - Quantizing Recurrent Language Models Is Easier Than You Think Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01864 - Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02009 - Tracing the Scientific Discovery Capacity of LLMs to Their Training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03617 - LLMs struggle to simulate human belief updates in controlled environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28347 - TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02810 - Same Sentence, Different Construct: Identity-Swapped Rationales Reveal Measurement Non-Invariance in LLM Hate Speech Classifiers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02491 - Leveraging Recourse and Size Bounds for OnlineKnapsack with Removable Items Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40290 - Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00442 - Geometry of Confabulation and Refusal in Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01272 - AI-Enabled Question-Answering for Chartered Accountancy: A Retrieval-Augmented Reasoning Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00257 - From Language to Country to Valence: A Multilingual Audit of Stereotype Bias Across LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02585 - When Answer Evaluation Misleads Confidence Selection: Fact-Grounded Form Grading for Open-Ended QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25654 - IndicDBBench - Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13686 - An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.03093 - A State Change Is Local, Its Consequences Are Not: Dependency-Aware State Revision for Long-Term Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02912 - A Systematic Analysis of Live Intraoperative Surgical Expert Narrations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00028 - ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00871 - To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02002 - AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26998 - CheXPoT: Post-Hoc Visual Verification and Correction of VLM-Generated Radiology Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00785 - CST: Lightweight Risk Triage with Source-Grounded Evidence for Web Discussions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01710 - Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00006 - Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29319 - Towards Fine-grained and Robust Detection of Human-AI Co-authorship Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01427 - DiabAgent: Toward Agentic Physiological Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03601 - SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25990 - Pacing Branch Parallelism in LLM Serving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06914 - Selection Shapes the Boundary: A Replication of Monotonicity and Label Agreement in Unselected NLI Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19231 - Solver-Like Behavior in Large Language Models as Formalizers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02395 - TOPol: Reconstructing and Interpreting Multidimensional Semantic Polarity Fields Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25069 - Re$^3$Rank: Listwise Reranking with Reasoning-Conditioned Retrieval Heads Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02550 - WeSearch: A Unified Model-Centric Retrieval Framework for WeChat Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00530 - Probing the Limits of the Lie Detector Approach to LLM Deception Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10003 ## Community - Is it possible to use `Iterator::map` in a ToSocketAddrs impl? (associated types involving closures) Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/is-it-possible-to-use-iterator-map-in-a-tosocketaddrs-impl-associated-types-involving-closures/143465 - CLI project structure in Rust Source: rust-users-forum Topic: Rust URL: https://users.rust-lang.org/t/cli-project-structure-in-rust/143464 - Wing Tips: Getting Started with Autonomous Development in Wing Pro 12.1 Source: planet-python Topic: Python URL: https://wingware.com/blog/agent-autonomous - Graham Dumpleton: Twenty years of mod_wsgi, and what comes next Source: planet-python Topic: Python URL: https://grahamdumpleton.me/posts/2026/11/twenty-years-of-mod-wsgi/ - An 80-Cent Plastic Pouch Is Saving Women from Dying in Childbirth Source: hacker-news Topic: General URL: https://www.nytimes.com/2026/11/03/health/maternal-drapes-nigeria-childbirth.html - Jelly Sheet Source: hacker-news Topic: General URL: https://mrdoob.github.io/codevember-2026/01/ - Distinct cellular and genetic differences in colorectal cancer in young patients Source: hacker-news Topic: General URL: https://www.dana-farber.org/newsroom/news-releases/2026/study-reveals-distinct-cellular-and-genetic-differences-in-colorectal-cancer-in-younger-patients - Arrows to arrows, categories to queries (2025) Source: hacker-news Topic: General URL: https://reasonablypolymorphic.com/blog/arrows-to-arrows/ - Tell HN: Don't use Postman, they proxy your info without your permission Source: hacker-news Topic: General URL: https://news.ycombinator.com/item?id=50360947 - Giant canyon on Mars is still tectonically active Source: hacker-news Topic: General URL: https://lamont.columbia.edu/news/giant-canyon-mars-still-tectonically-active-today - C++26 Disapproved Source: hacker-news Topic: General URL: https://andreasfertig.com/blog/2026/11/cpp26-dis-failed-how-does-cpp-survive/ - French blood storage facilities targeted in cyberattack Source: hacker-news Topic: General URL: https://twitter.com/etnshow/status/2117728420477936043 - Tesla allegedly misled South Korean customers about automated-driving tech Source: hacker-news Topic: General URL: https://www.reuters.com/business/autos-transportation/tesla-misled-south-korean-customers-about-automated-driving-tech-consumer-group-2026-11-04/