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: 27248 papers — Page 129 of 545
Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments
Oct 10, 2026
1 authors
cs.AIcs.CR
Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations
Oct 10, 2026
3 authors
cs.CL
Sensor-Aware Joint Data Fusion and State Estimation under Sparse Multi-rate Distribution Grid Sensing
Oct 10, 2026
4 authors
cs.LG
Learning Proposition-Level Links from Sentence-Level Supervision for Neuro-Symbolic NLI
Oct 10, 2026
2 authors
cs.CL
Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models
Oct 10, 2026
2 authors
cs.LG
Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry
Oct 10, 2026
3 authors
cs.CLcs.LG
LexiCan: Lexicographic Canonicalization of Point Clouds for Machine Learning Applications
Oct 10, 2026
7 authors
cs.LG
Physics Foundation Models for Efficient Control of Fluid Flows
Oct 10, 2026
3 authors
physics.flu-dyncs.LG
Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents
Oct 10, 2026
7 authors
cs.LGcs.CR
Word-Aligned Prosody Reflects Speaker Differences More Than Depression or PTSD Severity
Oct 10, 2026
5 authors
eess.AScs.CLcs.SD
Game-Theoretic Reinforcement Learning based Topology-Agnostic Defense for Virtual Power Plants
Oct 10, 2026
4 authors
cs.LGeess.SY
SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG
Oct 10, 2026
1 authors
cs.CLcs.LG
Continuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals
Oct 10, 2026
3 authors
cs.AIcs.CYcs.MA
Do LLMs differentiate linguistic traits internally?: A layer-wise analysis
Oct 10, 2026
4 authors
cs.CL
SocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair
Oct 10, 2026
3 authors
cs.AIcs.LG
MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning
Oct 10, 2026
5 authors
cs.ARcs.IRcs.LG
Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models
Oct 10, 2026
2 authors
cs.LGcs.AIcs.CL+1
PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
Oct 10, 2026
6 authors
cs.CLcs.AIcs.IR
Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models
Oct 10, 2026
5 authors
cs.AI
HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems
Oct 10, 2026
4 authors
cs.AI
Understanding Unified VLMs: From Attention Probing to Guidance Tuning for Multimodal Generation
Oct 10, 2026
6 authors
cs.AI
Using Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration with Automated Essay Scoring
Oct 10, 2026
4 authors
cs.AIcs.HC
Inverse Synthesis of Shock Time Series from Shock Response Spectra Using Ensembles of Conditional Variational Autoencoders
Oct 9, 2026
5 authors
cs.LGeess.SP
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Oct 9, 2026
5 authors
cs.AIcs.CRcs.MA
When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks
Oct 9, 2026
8 authors
cs.CL
TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents
Oct 9, 2026
5 authors
cs.LG
Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions
Oct 9, 2026
2 authors
stat.MLcs.LG
Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target
Oct 9, 2026
6 authors
cs.LG
Structure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-Localization
Oct 9, 2026
6 authors
cs.CV
COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
Oct 9, 2026
2 authors
cs.CLcs.AIcs.LG
Fear Is Not Always Fear: Variation in Emotion Label Equivalence Across Datasets
Oct 9, 2026
2 authors
cs.CL
Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests
Oct 9, 2026
2 authors
cs.SEcs.AI