TILens Daily Edition
2026-08-29
Filters: topic=ai, github=hidden

Stats: 317 articles, 4 sources, 315 research papers
Top topics: AI, AI Research, Python

## News

- Presentation: Architecting the Data Layer for AI Agents: from Transactional Systems to MCP and Semantic Models
  Source: infoq-architecture
  Topic: Architecture (+AI)
  URL: https://www.infoq.com/presentations/enterprise-data-architecture-ai-agents/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design

## Research

- 4 Claude Skills Every Data Scientist Needs in 2026
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/4-claude-skills-every-data-scientist-needs-in-2026/

- When to Use Claude Code and When to Use Codex
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/when-to-use-claude-code-and-when-to-use-codex/

- RAG Is Not the Whole Toolkit: The NLP Techniques Real Problems Still Need
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/rag-is-not-the-whole-toolkit-the-nlp-techniques-real-problems-still-need/

- No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Task
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.16514

- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.10358

- TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27282

- Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26199

- LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.14496

- Knowledge Cards: Structured Knowledge for AI Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26176

- Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26807

- SWE-Prime: Fewer Trajectories, Better Performance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27449

- Multi-Person Human Motion Forecasting in Complex Scenes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27039

- Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.10002

- Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counseling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.02950

- DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26757

- Co-Evolving Structured Knowledge and Reasoning in Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26386

- Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26142

- When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26187

- A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26949

- Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26306

- LLMs Can Design Near-Optimal OR Algorithms
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27296

- MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.06270

- Toward a New Science of AI as Cognitive Infrastructure
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.22893

- LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26849

- PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27345

- The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26423

- Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27309

- CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26656

- 6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26236

- Egosurg: Arbitrary view synthesis for egocentric replay of operating room workflows from ambient cameras
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.04802

- Fine-Tuning of Transformer models with Frames
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26430

- MedFabric: Gold Evidence Hides the Difficulty of Word-Level Medical Fabrication Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.04180

- Explainable Artificial Intelligence for Customer Churn Prediction in Telecommunications: A Framework for CRM Integration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26151

- Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26165

- Diff Mining: Logit Differences Reveal Finetuning Objectives
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26462

- Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26418

- Pixel Wised Lesion Prediction on COVID-19 CT Imagery: A Comparative Analysis of Automated Image Segmentation Architectures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20459

- Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27340

- Cartan flow matching
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.03588

- FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26310

- From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27442

- Omni-Interactive Universal Embedder
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27044

- From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24368

- FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26129

- LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27184

- Compositional Online Learning for Semantic Data Processing Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27244

- Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26535

- Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26710

- Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26743

- A Task-Centric Ontology and Deterministic Domain Rules as a Verifiable Core for AI-Assisted Chemistry Problem Solving
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26164

- 4DStreamCtrl: Interactive Video Generation with Online 4D Control
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.25479

- The BS-meter: Detecting Politics and Labour through ChatGPT's Language
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2411.15129

- When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.04893

- Recurrent Reinforcement Learning with Memoroids
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2402.09900

- How Language Models Organize and Structure Moral Knowledge
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27402

- Large Models for Battery Prognostics and Health Management: A Review and Future Roadmap
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26111

- Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.02357

- ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.18037

- Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27427

- From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26950

- Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26694

- Communication styles and reader preferences of LLM- and human-authored COVID-19 information explanations: a case study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.08143

- pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27101

- When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27146

- Invocation-Level Reliability of Tool-Using Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26189

- MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Prediction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.21957

- Accelerating Scientific Research with Gemini in the Real-World
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26701

- AI Revealed Preferences
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26178

- From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26856

- DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26990

- BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27268

- NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26222

- Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.16105

- From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23045

- CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.14586

- Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26385

- When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.25553

- Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26225

- The Limits of Automatic Evaluation of Creativity in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23705

- Stageboost: Recommending Signals Based on Counterfactual Estimation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27366

- Comparing Chunking and Embedding Strategies for Turkish RAG Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26192

- AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Scenes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26193

- ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26991

- Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27367

- BPMN4CAI: A BPMN Extension for Modeling Dynamic Conversational AI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27149

- Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26674

- RCMN: Understanding Misleadingness in Influential Public Discourse
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27358

- Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.03345

- Summarization is Not Dead Yet
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.08000

- Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26191

- Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26190

- High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.23940

- MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13463

- LiveVVT: High-Fidelity Video Virtual Try-On in Real Time
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26714

- Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27421

- Complexity Induction: Compositional Generalization via Structured Training Distortion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.21464

- SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22018

- MIMO: Multilingual Information Retrieval via Monolingual Objectives
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.31171

- How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26327

- Learning the ARTS of Search for Automated Discovery
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21891

- Categorizer Automata for Discounted-Sum Payoffs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26763

- The Reasoning Tax: Token Economics of LLM Reasoning Across Task Types and Deployment Contexts
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26235

- CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27406

- Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27424

- Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26732

- A Very Big Video Reasoning Suite
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.20159

- Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26885

- ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27150

- Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27167

- ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23478

- A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27086

- Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20768

- Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03611

- Agentic AI for operating scientific instruments for nanoscale characterization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26198

- Recurrence Meets Transformers for Universal Multimodal Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.08897

- What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.25732

- SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.18801

- Beyond Linearization: Attributed Table Graphs for Table Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.08444

- Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26480

- When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27176

- LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.04438

- Rethinking the Evaluation of Harness Evolution for Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.12227

- GameWAM: A World Action Model for Video Games
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26200

- Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10954

- STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27225

- AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26747

- Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27266

- Assessing mentalization in humans and large language models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26291

- HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.17873

- ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22559

- BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26867

- Active sensing to characterize the heterogeneity of plant stress
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27088

- On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26292

- Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.15439

- Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23149

- Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.10402

- MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26848

- CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24947

- Investigating the Influence of Prompt and Response Languages on LLM Content Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26186

- Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reuse
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26149

- Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27429

- RTNav: Towards Real-Time Zero-Shot Object Navigation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26496

- MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.25457

- Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.25529

- J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26582

- SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.03230

- A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imagery
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20445

- Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditions
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27392

- Five Primitives for Governing Autonomous AI Agents at Runtime
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26696

- C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26870

- TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.11637

- FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26676

- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27454

- GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27142

- The Principles of Diffusion Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.21890

- EduRiskX: A Neuro-Symbolic Framework with F-Logic Reasoning for Early Academic Risk Prediction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26107

- REPREC: Representation Driven Parameter-Efficient Recommendation System
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.24845

- Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27066

- Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27141

- Selection Bias Correction in Retail Intelligence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26156

- Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23098

- Learning New Facts with QLoRA: An Acquisition-Retention Frontier
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.25677

- Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26317

- Simultaneous Envy and Equitability Guarantees
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26410

- MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26295

- Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26143

- Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26161

- LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27395

- Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.14892

- When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26895

- A 12-CNOT Double Qubit Excitation Gate
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11733

- How LLMs Distort Our Written Language
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.18161

- Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.17173

- Pre-training Visual Dexterity in Simulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15917

- LAAF: A Layered Accountability Architecture Framework for LLM Applications
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27102

- Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26549

- Magnon-induced phononic Chern insulator
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27011

- Refusal Is Not Robustness: Auditing Confident Fabrication in Large Language Models on a Provably Uninformative Clinical Pain Speech Transcript
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26167

- Account Consistency from Gameplay Traces: Same-Player Verification in Counter-Strike 2
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24893

- DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.08586

- PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27206

- Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26846

- CollaFuse: Collaborative Diffusion Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2406.14429

- RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24275

- EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23758

- PailitaoGR: Latent Think-with-Images for Generative Image Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26658

- Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26889

- A Multi-Framework Comparison of Outline Stages in Long-Form Generation with LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26177

- Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22642

- SKILL.state: Scalable Long-Horizon Agent Skills
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26263

- Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Search
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26152

- Designing Cellular Manufacturing Systems in the Presence of Alternative Process Plans
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2411.15361

- X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.16658

- Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26166

- GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18475

- DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.25061

- Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.15810

- GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.25160

- Risks and Controls for Multi-Agent Systems: an analytical framework for deployment of AI agents across organisational boundaries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26626

- Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26125

- Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26168

- Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26182

- Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.21599

- CG4AI: A Column Generation Framework for Training AI Models Under Constraints
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26375

- Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.02324

- TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23838

- Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26188

- A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26194

- AI Control Scientist: LLM-driven Agentic System for Automated Control Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26780

- DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26172

- HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.15740

- Temporally-Grounded Language Generation: Towards Real-Time Vision-Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.11326

- Thomson: Continual Learning of Frontier Models for SovereignAI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27147

- Reinforcement Learning-Based Control of CAV Platoon Joining Maneuvers in Mixed Traffic
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26860

- AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26623

- Sophistication in GenAI Use: Field Evidence from a Large Firm
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27364

- Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26175

- LoRA as Oracle
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.11207

- Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27397

- When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.23780

- Counterfactual Bias Testing for Application Tracking System
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26899

- AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26713

- A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.13427

- Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26209

- Subspace Alignment for Vision-Language Model Test-time Adaptation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.08139

- Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27747

- SAREF-based Ontology for Distributed AI Workflows across the Edge-Fog-Cloud Continuum
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26160

- Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27311

- Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26372

- SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26432

- SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26683

- PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.02897

- Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.04562

- Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26730

- GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26983

- Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.00908

- A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27010

- Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2504.05216

- Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27080

- GROUND: Reducing Hallucinations in LLM-Based Enterprise Analytics Through Governed Semantic Definitions
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26157

- Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26159

- Unsupervised Post-Training of Foundation Models: A Survey
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24982

- Syntax vs. Semantics: How Transformers Learn Deep Dependencies
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26139

- How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26237

- AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.11515

- PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26882

- FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26746

- Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27144

- Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.12631

- Learning to Predict, Discover, and Reason in High-Dimensional Event Sequences
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.16313

- The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26116

- SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26836

- Performance Foundations of Parallel & Distributed Reasoning Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27046

- Emotional Preferences as Goal-Priority Regulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27072

- Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.06753

- FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27021

- FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20574

- KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27365

- Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26733

- NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07167

- Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26221

- CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26114

- TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26184

- ClassVision: AI-Powered Classroom Attendance System
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26173

- Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.18064

- PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26530

- DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26546

- Discovering Relationships in Data Lakes Using Large Language Models: An Industrial Case
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26750

- M-Net: Integrating Spectral Features and Physical Field Operators into Deep Learning for Medical Image Segmentation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12196

- Nomad: Autonomous Exploration and Discovery
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.29353

- Same Model, Different Harness: Different Coding-Agent Results
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26218

- Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26753

- Learning Transverse Momentum Distributions from Raw Scattering Events via Conditional Diffusion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27077

- From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26117

- Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.00611

- LLM Agents for Time-Series: A Survey
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26226

- Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26109

- EEG-to-Report: An Annotation and Feature-Text Framework for Training Language Models on Clinical EEG
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26153

- Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22963

- Leveraging Large Language Models for Systematic Literature Review of Disease Spread Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26150

- LLMs for Academic Workflows: An Evaluation of Literature Reviews Generated with Short and Long Context Windows of LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26145

- RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27439

- What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27260

- ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26334

- Exploring the Role of LLMs in HPC Programming: A Survey
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26110

- TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27127

- VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26155

- Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGS
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26951

- Blast Radius
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07440

- From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.22203

- Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26442

- From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.23955

- Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19020

- PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26113

- MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.18383

- ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDB
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07945

- REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11698

- The Accuracy-Efficiency Paradox Quantifying Net Energy Loss in on-Device Energy Forecasting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26134

- Decoupling Planning and Control for Instructable Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26788

- CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.27391

- Evaluating AI Generated Summaries for Cancer Patients
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26154

- ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26204

- DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.12979

- LLM-Specific Utility for Retrieval-Augmented Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.11358

- Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.11017

- CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.04778

- PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26180

- From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26163

- A Safety-Gated Multimodal AI Backend for Mental-Health Support: Hierarchical State Representation, Conservative Risk Fusion, and Controlled Generation in Anian
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26162

- MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.20468

- AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26896

- Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26346

- UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-on
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05745

- Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26185

- Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.24135

## Community

- Introducing Hy4 Preview
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/29/hy4/