TILens Daily Edition
2026-08-15
Filters: topic=ai, github=hidden

Stats: 301 articles, 2 sources, 299 research papers
Top topics: AI, AI Research, Python

## Research

- The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13520

- CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12842

- MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.00048

- Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.13325

- Error-Aware Reverse Auction Mechanism for Large Language Model Routing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12719

- CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09164

- Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.28166

- IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.16399

- Doctorina MedBench: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.25821

- LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12321

- AutoQuREO: A Framework for Automated Quantum Resource Estimation and Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12936

- vToken: Token-Level Virtualization for Reclaimable KV Caches
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13263

- Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13417

- Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10473

- Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13447

- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09696

- Memorization Diagnostics for Code LLMs Should be Scale-Aware
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12771

- Query Timing Produces Opposite Positional Biases Between LLMs and Humans
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12387

- @skills: Attention is all you have
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12610

- Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12599

- Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12921

- EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13072

- When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12324

- Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13256

- The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12677

- A Hierarchical Energy-Based Model for Multimodal Cognition
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12398

- Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.04997

- Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12372

- DomusFM: A Foundation Model for Event-Based Behavioral Monitoring in Smart-Homes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.01910

- Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13315

- Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12892

- Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12831

- Foundations of MT-PDCL: Measure-Theoretic Probabilistic Definite Clause Logic
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13018

- Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12961

- LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12626

- SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12429

- From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13043

- FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12932

- AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13560

- SchemaLink: An Intelligent Web Editor for LinkML Schema Curation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12529

- AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13492

- StreamReason-Bench: Can Large Language Models Reason about Event-Time Stream-Processing Semantics?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12348

- Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12679

- The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.02091

- On the Expressive Power of Transformers
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12671

- The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12959

- Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18852

- Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12590

- Do Transformers Need Three Projections? Systematic Study of QKV Variants
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.04032

- From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12350

- PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12762

- SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13173

- LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13333

- Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13250

- Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12597

- Safe Exploration via Policy Priors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.19612

- Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13156

- StorySpark: Module-wise Evolutionary Search for Story Premise Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12336

- Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12713

- Learning to Recover Task Experts from a Multi-Task Merged Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.26902

- MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11616

- Vibe to Code: Elucidating Strategic Oscillation of Tacit Knowledge in Generative AI Design Workflows -- An Exploratory Qualitative Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23126

- SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27431

- Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12368

- FluctlightDB: A Memory Model of Data for AI Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12365

- Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05018

- From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12836

- Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13426

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

- Deliberate Practice: Learning Robot Skills under a Budget
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13415

- The Hidden Evolution of Disguised Visual Context inside the VLM
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.20077

- MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.17228

- Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13394

- Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12851

- Static analysis-guided agentic AI translation enables Rust as a full stack bioinformatics language
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13029

- InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12915

- OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12995

- PIPES: Securing Agent Perception with Provenance and Priors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12789

- UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13031

- Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.00367

- OEIS Open: How many conjectures can language models turn into theorems?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11941

- UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13453

- LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.05031

- Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12806

- Residual Modeling for High-Fidelity Learned Compression of Scientific Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.05389

- Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12391

- Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12373

- From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.27906

- Cat-DPO: Category-Adaptive Safety Alignment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.17299

- Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2411.16818

- Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.01896

- SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12876

- Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13296

- NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13210

- StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.06200

- $\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12522

- Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11195

- Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.08322

- Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13305

- NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12898

- Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12585

- SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13120

- Communication Heterogeneity and Collective Consensus in Neural Cellular Automata
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21202

- iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06161

- Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12764

- Synthetic Persona Pretraining: Alignment from Token Zero
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13482

- A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13456

- Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.05678

- Cueless EEG imagined speech for subject identification: dataset and benchmarks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.09700

- SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12443

- Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03172

- A Distributional Robustness Margin For Pathology Foundation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.25497

- Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.22699

- Moral Hazard in Multi-Agent Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23982

- Operationalizing Cyber Threat Intelligence with GraphRAG
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13050

- It's How You Ask: Gender-Associated Linguistic Bias in LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13328

- AQuA: Recursively Self-Improving Quantitative Trading Research Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12841

- From Observation to Intervention: Memory in Brains and Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12377

- Generative Universal Multimodal Retrieval with Dual-role Identifiers
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12987

- Governing Agentic AI in FinTech
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11344

- Interaction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12358

- Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12476

- NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13293

- Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13129

- GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13255

- Research Assistant: AstraZeneca's Agentic System for R&D
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12395

- Falsehood and Impossibility Are Different Directions in an AI's Representation of Language
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12852

- Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.12532

- Automatic Termination Strategy of Inelastic Neutron-scattering Measurement Using Bayesian Optimization for Bin-width Selection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.16946

- Auditable Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.05485

- Identification of Probabilities of Causation: from Recursive to Closed-Form Bounds
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.15274

- Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19058

- Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.13372

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

- Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10766

- Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.23724

- PatientAct: Theory-Grounded Mental Health Client Simulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12750

- Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13277

- Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12345

- AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12329

- Automated Design Optimization via Strategic Search with Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.22651

- RadarGen: Automotive Radar Point Cloud Generation from Cameras
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.17897

- Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13410

- How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13267

- Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12645

- CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13226

- QuoteBench: How Matched Scores Can Hide Command-Path Failures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13547

- ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13438

- SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12751

- Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12674

- Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13430

- Humans are Missing from AI Coding Agent Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12355

- StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13317

- Assessment Design in the GenAI Era: The X1-X2-X3 Assessment Pattern for Testing Students' AI Literacy, Learning Outcomes, and Reflection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12351

- SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13076

- Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12385

- EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13113

- In-context superposition: human-like working memory interference in large language models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.09670

- Position: Reasoning is a Learnable Rule-Based Process
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12325

- Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12346

- Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.14573

- CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.22282

- Hamilton-Zero: A Neural Tensor-Network Foundation Model for Ground States of Arbitrary Quadratic Qubit Hamiltonians
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11911

- Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13179

- AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.26661

- Designing AI Pipelines for Decision-Ready ITSM Intelligence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12670

- Coordinated incentives in AI-generated misinformation governance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07070

- Personalized Scorer Modeling: A Learning-Based Framework for Deriving Robust Sleep Stage Labels from Multiple Experts
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12446

- CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12555

- Scaling Time Series Classification via XAI-Driven Data Reduction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.15774

- AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11392

- Learning Latency-Aware Orchestration for Multi-Agent Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.10560

- HybridSB-MoE: Dual-Domain Schr\"odinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12715

- Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12935

- REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.14390

- Do LLMs Know Their Vulnerable Scenarios?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23496

- TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13167

- Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12371

- PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.19799

- Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07335

- Architecture Before the Formula: Individuating Neural Architecture Beyond the Composite Map
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.11618

- Why AI Governance Frameworks Are Hard to Adopt: A Role-Based Stress Test of the NIST AI RMF
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12352

- Correct Is Not Governed: Provenance Integrity in Agentic Workflows
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12761

- ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12720

- A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.15489

- Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13484

- What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12322

- Algebraic Decomposition Theory for Transformer Length Generalization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13433

- Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI Interaction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.08443

- Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument Decides
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07316

- CAPRI: Contract-Aware Proof Repair for Isabelle
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13459

- Demand Transfer Estimation at Scale via Restricted Logit Modeling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12680

- SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.07820

- Novels generated by language models show compressed formal variation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12630

- LOB-ID: Evaluating Synthetic Market Data by Inception Distances
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13082

- Not All Nudges Land: Behavioral Controllability and Elaboration Quality in AI-Supported Journaling
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12582

- Interpretable Causal Discovery via Causal-Effect Constraints
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12640

- DiG-bench: Discovery in Games
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12593

- LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13344

- Unmasking Conversational Bias in AI Multiagent Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.14844

- Yes, Q-learning Helps Offline In-Context RL
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.17666

- SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12654

- BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13046

- Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12977

- Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12426

- 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

- Recursive Synthesis for Long-Horizon Terminal Tasks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05466

- Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10805

- Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13160

- CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.14501

- Vision-Language Models are Fragile Multilingual Associators
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12333

- DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13048

- Nutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10363

- Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13420

- Steering the Language Axis: From Linear Decodability to Causal Control
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12334

- How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.06331

- Time-Series Forecasting in Safety-Critical Environments: An Open-Source Package for EU-AI-Act-Compliant Development / Zeitreihenprognose in sicherheitskritischen Umgebungen: Ein Open-Source-Paket f\"ur die KI-VO-konforme Entwicklung
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.23859

- Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention Matching
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12331

- Measuring Curriculum-Labor Market Alignment at the Scale of a Program Portfolio
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12356

- Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12843

- MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13476

- DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13517

- Annealed Softmax Greedy in Many-Armed Bayesian Bandits
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.31034

- Keep the Future, Drop the Rollout: RIFT for World Action Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11521

- Multi-Layer Context Camouflaging: A Semantic Superposition and Contextual Lamination Framework for Malpractice-Resilient Online Assessment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13100

- H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12926

- Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12389

- Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.17337

- Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13087

- TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09538

- Vero: Can AI Agents Build Formally Verified Software Repositories?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13522

- Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13228

- Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12847

- Explanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI)
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13063

- Sovereign by necessity? Frontier AI export controls, cyber security, and the limits of national AI capability
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13272

- Rules or Character? Scaling Laws for AI Safety Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13345

- Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12374

- BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12854

- CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12779

- Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.12220

- Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12895

- Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12218

- AI and Consumer Rights in India Working Paper
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12863

- RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13428

- Training AI Scientists to Replicate Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13331

- Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13283

- What Makes a Peer? Valuation-Anchored Similarity in Private Markets
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12594

- SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.16454

- Uniform Herding: Exemplar Replay with Representation Refresh
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13061

- INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20088

- VALG: An Agentic System for ML Theory Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13060

- Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12440

- CEON: Circular Economy Ontology Network
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.02253

- FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12845

- Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13341

- DiffGRM: Diffusion-based Generative Recommendation Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.21805

- Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13368

- SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.17985

- General Probabilities of Causation with Causal Knowledge
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12657

- EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12363

- PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12600

- The AI Accountability Ecosystem in the Era of Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12320

- DAPD: Dual-Anchored Policy Distillation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01735

- DiffImaginE: Imagine to Verify Entity Types with Diffusion
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03025

- Constitutional On-Policy Safe Distillation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.03089

- TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13221

- HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13555

- ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12788

- Concept Drift Detection and Adaptive Retraining of Malware Classification Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13465

- EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12906

- Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12323

- GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13200

- Early Warning Signals for OpenVLA Failure under Visual Distribution Shift
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.29699

- MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12428

- LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13136

- Robust Dempster-Shafer Evidence Fusion with Chaos-Conflict Measurement and Historical-Experience Weighting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13108

- Jointly Predicting Courses and Grades Using a Transformer-Based Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13409

- LipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Service
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13144

- Into the ORBIT for Time Series: Training Regimes for Foundation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13262

- EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12627

- Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13258

- OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13558

- Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12675

- Trie Automata for Constrained Decoding over Large Finite Sets
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12574

- AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.08756

- A Compositional Theory of Curvature in Probabilistic Circuits
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12869

- TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topologies
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13389

- Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12689

- AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13472

- Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12441

- Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12880

- Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18793

- Mimicry without understanding: the origins of decision bias in large language models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12339

- Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13069

- TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13057

- Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12327

- Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12743

- ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12877

- Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evidence
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12928

## Community

- CORS Chat
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/15/cors-chat/

- Northern Gannet
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/15/sighting-391300422/