AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 27748 papers — Page 96 of 555
Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests
Oct 13, 2026
3 authors
cs.CRcs.AI
Correcting or Continuing? What On-Policy Distillation Learns from Student Errors
Oct 13, 2026
4 authors
cs.LGcs.AI
LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems
Oct 13, 2026
7 authors
cs.CLcs.AI
Dynamic Interpolation for Training-Time Prediction Reshaping in Low-Light Image Enhancement
Oct 13, 2026
5 authors
cs.CV
Machine--human agreement in marking undergraduate assignments is specific to model, prompt and institution
Oct 13, 2026
7 authors
cs.CL
FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation
Oct 13, 2026
9 authors
cs.LG
SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces
Oct 13, 2026
3 authors
cs.AIcs.LG
ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression
Oct 13, 2026
7 authors
cs.LGcs.AI
Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On?
Oct 13, 2026
7 authors
physics.chem-phcs.AIcs.LG+1
FlowSim: Rendering-Free Closed-Loop Simulation for Evaluating End-to-End Driving Systems
Oct 13, 2026
4 authors
cs.CV
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection
Oct 13, 2026
7 authors
cs.CV
Weighting-Based Strategies for Classification: Analysis and Local Peak Dynamics with CART Trees
Oct 13, 2026
3 authors
stat.MLcs.LG
Data-Free Continual Learning for World Action Model with Rectified Generative Replay
Oct 13, 2026
8 authors
cs.ROcs.CV
Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression
Oct 13, 2026
4 authors
cs.CVcs.AI
High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics
Oct 13, 2026
5 authors
physics.flu-dyncs.AIcs.LG
inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
Oct 13, 2026
6 authors
cs.LGcs.AIcs.CL
Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
Oct 13, 2026
7 authors
cs.AI
Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryption
Oct 13, 2026
5 authors
cs.CRcs.LG
From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning
Oct 13, 2026
3 authors
cs.LGcs.AI
Uncertainty Evaluation: Bridging Machine Learning and Measurement Science
Oct 13, 2026
2 authors
cs.LGcs.AI
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Oct 13, 2026
17 authors
cs.AIcs.LG
Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
Oct 13, 2026
4 authors
cs.LG
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Oct 13, 2026
7 authors
cs.LG
AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
Oct 13, 2026
14 authors
cs.AI
Same Function, Different Trajectory: No Standard Optimizer Is Equivariant to Transformer Reparameterization
Oct 13, 2026
1 authors
cs.LGcs.NE
ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
Oct 13, 2026
4 authors
cs.AIcs.LG
AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses
Oct 13, 2026
6 authors
cs.AI
LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
Oct 13, 2026
9 authors
cs.AI
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
Oct 13, 2026
7 authors
cs.AIcs.CRcs.HC
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
Oct 13, 2026
8 authors
cs.CVcs.AI
From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits
Oct 13, 2026
2 authors
cs.LG
SYNPRED: A Synergistic Approach to Multimodal Learning for Clinical Prediction
Oct 13, 2026
9 authors
cs.LGcs.CV
When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Oct 13, 2026
7 authors
cs.LGcs.AI
Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering
Oct 13, 2026
5 authors
cs.CL