TILens Daily Edition
2026-11-10
Filters: topic=ai-research, github=hidden

Stats: 159 articles, 4 sources, 150 research papers
Top topics: AI, AI Research, Python

## News

- Who’s Investing in Anthropic’s IPO? Inside the $26 Billion Tech Bet
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/whos-investing-in-anthropics-ipo-inside-the-26-billion-tech-bet/

- The Hundred-Page Deep Reinforcement Learning Book is now available for purchase!
  Source: true-positive-weekly
  Topic: AI (+AI Research)
  URL: https://aiweekly.substack.com/p/the-hundred-page-deep-reinforcement

- NVIDIA’s GR00T 2 Learns From Human Video. Can That Make Robots Scale?
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/robotics-insider/nvidia-gr00t-2-human-video-robot-learning/

- Australia’s AI Safety Plan Puts Reporting, Evaluations and Penalties on the Table
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/australia-ai-safety-laws-medicare-agent-breach/

- What Scientists Can—and Still Can’t—Learn From AI’s Inner Workings
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/explainer-articles/mechanistic-interpretability-ai-safety/

- 😺 Anthropic released Claude Fable 5.2
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/newsletter/anthropic-released-claude-fable-5-2/

- OpenAI Built Control Room to Stop AI Experiments That Go Wrong
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/openai-control-room-stop-ai-experiments/

- Fireworks AI Was Hacked. Here's How Criminals Make Money From Stolen AI Access
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/fireworks-ai-breach-stolen-ai-access-llmjacking/

- Everything That Happened in AI Today (Tuesday, November 10, 2026)
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-tuesday-november-10-2026/

## Research

- Scikit-Learn Matched or Beat Jev's Calibration on BANKING77
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/scikit-learn-matched-or-beat-jevs-calibration-on-banking77/

- A Session-Start Hook Raised Claude Code Skill Firing From 15% to 62%
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/a-session-start-hook-raised-claude-code-skill-firing-from-15-to-62/

- How to Validate LLM Output in a DuckDB and dbt Pipeline
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/how-to-validate-llm-output-in-a-duckdb-and-dbt-pipeline/

- Copilot Caught 8 of 8 Diff Bugs With Rules, 0 of 2 Outside the Diff
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/copilot-caught-8-of-8-diff-bugs-with-rules-0-of-2-outside-the-diff/

- How Much Conversation History Does an AI Agent Need?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09662

- LLMs as Judges and Examinees for Medical Item Difficulty Prediction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.38402

- Does Reasoning Improve Psychological Depth in Large Language Models?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09061

- PhoPunct: A Large-Scale Benchmark of Transformer Architectures for Vietnamese Punctuation Restoration
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09107

- Jacobian-Causal Memory Control for Persistent Memory in Language Model Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08779

- Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08971

- SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.24371

- CodeQuant2: Enhanced Outlier Mitigation and Adaptive Clustering for Low-Precision LRMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09868

- Subliminal Learning in Vision-Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08538

- DUET: Dual-Sparse Inference for Block Diffusion Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09239

- RPEG: Training Reasoning Language Models Scalably and Cost-Effectively
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09207

- ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08669

- Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07234

- Calibrated concept profiles: making the reading of a model's neurons a measurement
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09196

- Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.11651

- Structure and Lineage Evidence for Vietnamese Statutory Article Retrieval on DRiLL
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09200

- SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08790

- Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.19150

- Representational drift in a code model: behaviour settles, which neurons carry it does not
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09204

- Contextuality and Contradictions: Exploring Real-World Identifications of AI-Generated Writing
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08704

- Improving Contextual Retrieval for Long Documents using Semantic Chunking and Hybrid Retrieval Strategies
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08498

- A Taxonomy-Driven Synthetic Dataset for Retrieval Effectiveness and Fairness Evaluation in Hiring
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09178

- L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.00761

- Beyond Truncation? Entailment-Licensed Elision and the Limits of Semantic Preservation in LLM Decoding
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08975

- Structure is in the zoom: probing neural symmetry through dimensionality scaling
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08506

- Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.28031

- BMMS: Policy-Conditioned Measurement of Behavioral Compliance in Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09147

- Enabling Privacy-Preserving Natural Language Access to Industrial Smart Meter Data
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09372

- Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDP
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08639

- Learning to Simulate Individuals from Macro Social Signals
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.07062

- Signals Are Present, Predictions Fail: Probing Diagram Representations in Large Vision-Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.02865

- Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.05278

- A Spiking Neural Model of the Mental Lexicon: Representations, Similarity Structure, and Associative Retrieval in Perception and Production
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09402

- Prompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.38076

- ResQAdam: Residual-Preserving Adaptive Optimization for Memory-Efficient Quantization Aware Training
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08924

- Fine-Tuned Language Models Exhibit Improved Information Conveyance
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.30844

- An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.07755

- BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09505

- Measuring Weak-to-Strong Legibility of Reasoning Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.20508

- Structuring Survey Histories for LLM Digital Twins: A Controlled Study of Background, Decision Procedure, and Evaluation Profiles
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08730

- On the Effectiveness and Limitations of Open-Weight LLMs for Low-Resource Offensive Language Detection in Danish
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09506

- DunbaaBERT: From Sacrifice to Semantics
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.26935

- Compression of Emotion in Language Model Representations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08683

- What Makes a Question Curious? Measuring Model Curiosity in Human-LLM Interactions
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.33950

- Curved Knowledge in Flat Models: Building Expert AI at Scale
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.17513

- Khmer PFGen-Bench: Building a Judge-Free Benchmark for Open-Ended Generation in a Low-Resource Language
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09222

- VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10875

- Consolidating Rewarded Perturbations for LLM Post-Training
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.31494

- RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08162

- Guardrail Erosion in Domain Fine-Tuned Large Language Models: A Paired Audit of Knowledge-Centric Abstention in Biomedical LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08780

- Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09634

- An Effective Spoken Language Understanding Approach Leveraging Query-Adaptive Intent Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09491

- Wind Turbine Maintenance Log Labelling Framework: LLM-Driven Data Correction and Enrichment via Semantic Extraction of Reliability Intelligence
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.31281

- Richness Is Not Evenness: Ordered Renyi Crossings under Self-Training
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08892

- Decomposing Yes-No Bias in LLM Moral Judgment: Stance, Position, Word, and Verdict
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.05552

- From LoRA to Language: Recovering Skill Documents from Adapters
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09454

- Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.42039

- Can LLMs Take Retrieved Information with a Grain of Salt?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.06919

- Using an LLM to Tackle Difficult Cases in NER for Nepali Tweets
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08967

- Multilingual Artificial Datasets for AI-Driven Cardiology: the CliTe and ParaCliTe corpora
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09296

- Greedy Byte-Pair Encoding Achieves at Least 0.361 of the Optimal Compression
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08671

- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.02474

- RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09709

- How far does a hash-only sender go? A pre-registered map of sender memory versus bits for short text messages
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09848

- Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08706

- RuACT: Recovering Inactive Rubrics as Adaptive Critics and Teachers
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09597

- Outgrowing the Curse of Multilinguality: Scaling Strategies for Efficient Language Adaptation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.10772

- AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08752

- BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09825

- 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

- HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.04996

- How Small Can We Go? Calibrating Activation-Cache Compression for SAE Training
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08551

- Safety and accuracy diverge across deployment conditions in clinical large language models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.04039

- From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.10147

- Same Facts, Different Remedy: Linguistic Profiling and Arbitrariness in LLM and System One Decisions
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08995

- MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.25342

- On Seeding Watermarks to Detect Verbatim LLM Copy-Paste Responses
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.16336

- 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

- MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09721

- Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.35581

- Query-Guided RoPE Modulation for Lost-in-the-Middle Mitigation in Long-Context LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09554

- Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.17228

- Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.18413

- Patching the Blind Spots: Reversible LLM Rule Overlay for Frozen Fraud Detectors
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08714

- KLEAR: Knowledge-Matched LLM Evaluation in Korean across Application Requirements via Controlled Benchmark Transformation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09223

- Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.22688

- Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.25959

- ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09770

- CoBit: Language Modeling with Bitstream Diffusion
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07013

- AlienBench: A Benchmark of Structural Novelty in Language Model Outputs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09094

- LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.11748

- 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

- Syn2DRE: Synergistic Dual Teacher-Student Framework for Document-level Relation Extraction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09342

- Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19181

- Maya a1: Do the Options Read the Model, or Does Their Position? Order Sensitivity in a Non-Autoregressive Decision Model
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09803

- Language, Not Code Abstraction: Natural-language Training Shapes Brain-aligned Geometry
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09027

- The Invisible Gap: Romanized Indic Generation Fails Where Automatic Metrics Succeed
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09085

- Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.06840

- 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

- PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.13481

- PRISM: Stress-Testing Alignment-Faking Claims
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.13346

- Copies Are Not Confirmations: How News Duplication Fools LLM Judges and Continual Learners
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09203

- TraceSpec: Understanding and Improving Speculative Decoding for LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.41177

- Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.29463

- Measuring Form and Function in Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.28616

- Benchmarking Speaker Embedders in the Sub-Second Regime for Real-Time Voice AI Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09516

- Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.17102

- Continual Graph Memory and Community Infrastructure for AI-Assisted Mathematical Discovery
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02945

- Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09768

- PathXAI: Evidence-guided structured pathology reporting by transferable tissue segmentation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09117

- Negation Neglect: When models fail to learn negations in training
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.13829

- Compaction, decay and reinforcement in a two-tier conversational memory: a paired evaluation against retrieval-augmented generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09807

- Whispers from the Neighbors: Rethinking Caption Consensus as Inference-Time Evidence for Vision-Language Retrieval
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.33798

- Enabling Approximate Joint Sampling in Diffusion LMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.22738

- FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08643

- MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11316

- Archetypal contexts in the neurons of language models: an architecture for intelligence?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.07234

- Turkish Multimodal Video Fact-Checking: A New Dataset and a Comparison of Zero-Shot Agentic and Fine-Tuned Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08651

- Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11624

- LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13545

- Anatomy of LLM Sycophancy: What a Flip Rate Hides
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.06522

- ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09326

- Rethinking Data Selection as Distribution Matching on Semantic Manifolds
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08495

- Cognitive Maps in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.25596

- On the Incompleteness of do-calculus for Universal Identifiability
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08916

- The Consensus Trap: Collaborative Interleaved Generation to Defend against a Corrupted Majority
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.17139

- Internal Safety Collapse in LLMs and Coding Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.23509

- Asymmetric Correspondence Learning for Lexical and Style Embeddings: Interpreting Latent Space via Acoustic Features
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09313

- Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07847

- Real-Time Short-Response Selection for Spoken Dialogue Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09057

- Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.09630

- MARS: Training Multilingual Search Agents for Retriever-Free Evidence Acquisition
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09090

- Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.23170

- Are These Programmers Ripe Enough to Eat? Evaluating How LLMs Handle Lexical Knowledge Conflicts in Translation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09785

- Evidence-Linked Radiology Reporting: A Human-Supervised Reference Architecture for Structured Imaging Intelligence
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.25120

- AblationBench: Evaluating Automated Planning of Ablations in Empirical AI Research
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.08038

- Maswao: An automatically collected, prepared, and benchmarked dataset for South African Sign Language
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.02903

- BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.30646

- Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.08686

- Large Language Model Deployment on Resource-Constrained Edge Devices: A Practitioners Survey
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09075

- Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.09042

- RL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08711

- Semantic Conditional Similarity (SCS): A Formal Mathematical Framework
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08778

- Seeing vs. Counting: Complexity Twins Show Where Multimodal LLMs Fail on Diagrams
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08998

- From Procedures to Permissions: Learning Precise Subagent Authorization from Agent Skills
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2611.08905

- LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.18719