{"total":133,"rows":[{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2606.04990","title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","created":"2026-06-03","cited_by_count":37,"area":"agents"},{"id":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2602.11348","title":"AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"area":"agents"},{"id":"2601.15703","title":"Agentic Uncertainty Quantification","created":"2026-01-22","cited_by_count":19,"area":"agents"},{"id":"2607.09996","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","created":"2026-07-10","cited_by_count":18,"area":"agents"},{"id":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","cited_by_count":16,"area":null},{"id":"2602.17037","title":"Wink: Recovering from Misbehaviors in Coding Agents","created":"2026-02-19","cited_by_count":15,"area":"agents"},{"id":"2608.23041","title":"AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces","created":"2026-08-24","cited_by_count":15,"area":"agents"},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2603.06847","title":"Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes","created":"2026-03-06","cited_by_count":12,"area":"lr"},{"id":"2606.00765","title":"FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search","created":"2026-05-30","cited_by_count":12,"area":"lr"},{"id":"2601.15075","title":"The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution","created":"2026-01-21","cited_by_count":11,"area":"agents"},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","cited_by_count":11,"area":"agents"},{"id":"2605.29668","title":"GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents","created":"2026-05-28","cited_by_count":11,"area":"agents"},{"id":"2511.19933","title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","created":"2025-11-25","cited_by_count":10,"area":null},{"id":"2605.19196","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","created":"2026-05-18","cited_by_count":10,"area":"agents"},{"id":"2605.23311","title":"DART: Semantic Recoverability for Structured Tool Agents","created":"2026-05-22","cited_by_count":10,"area":"agents"},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2604.23581","title":"AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking","created":"2026-04-26","cited_by_count":9,"area":"agents"},{"id":"2605.26302","title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","created":"2026-05-25","cited_by_count":9,"area":null},{"id":"2607.18754","title":"AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents","created":"2026-07-21","cited_by_count":9,"area":"agents"},{"id":"2608.06346","title":"TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories","created":"2026-08-06","cited_by_count":8,"area":"agents"},{"id":"2510.14319","title":"Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction","created":"2025-10-16","cited_by_count":7,"area":"agents"},{"id":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2608.14380","title":"AgentRewind: Recoverable Execution for Long-Horizon LLM Agents","created":"2026-08-14","cited_by_count":7,"area":"agents"},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2604.14140","title":"LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning","created":"2026-04-15","cited_by_count":6,"area":"lr"},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2605.14892","title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2601.22984","title":"Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2603.02798","title":"Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification","created":"2026-03-03","cited_by_count":5,"area":"agents"},{"id":"2604.09678","title":"NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration","created":"2026-04-03","cited_by_count":5,"area":"agents"},{"id":"2605.17467","title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2605.22502","title":"Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost","created":"2026-05-21","cited_by_count":5,"area":"agents"},{"id":"2607.06184","title":"What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents","created":"2026-07-07","cited_by_count":5,"area":"agents"},{"id":"2608.06790","title":"AgentChaos: Chaos Engineering for Agent Systems via Programmatic Fault Injection","created":"2026-08-07","cited_by_count":5,"area":"agents"},{"id":"2512.04611","title":"PBFuzz: Agentic Directed Fuzzing for PoV Generation","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2601.11957","title":"PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning","created":"2026-01-17","cited_by_count":4,"area":"lr"},{"id":"2602.07187","title":"PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents","created":"2026-02-06","cited_by_count":4,"area":"agents"},{"id":"2603.01714","title":"TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2604.25135","title":"FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments","created":"2026-04-28","cited_by_count":4,"area":"agents"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.08563","title":"Why Retrying Fails: Context Contamination in LLM Agent Pipelines","created":"2026-05-08","cited_by_count":4,"area":"agents"},{"id":"2605.11225","title":"PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement","created":"2026-05-11","cited_by_count":4,"area":"agents"},{"id":"2607.06503","title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2608.02643","title":"CUADebug: Diagnosing and Repairing Computer-Use Agent Failures","created":"2026-07-31","cited_by_count":4,"area":"agents"},{"id":"2601.09393","title":"AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems","created":"2026-01-14","cited_by_count":3,"area":"agents"},{"id":"2603.20260","title":"ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2603.25100","title":"From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2604.23505","title":"Uncertainty Propagation in LLM-Based Systems","created":"2026-04-26","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.19240","title":"CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2605.29447","title":"Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents","created":"2026-05-28","cited_by_count":3,"area":"agents"},{"id":"2606.12329","title":"PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2608.22808","title":"CatchBench: When Can an Agent Failure Be Caught?","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2609.01360","title":"EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems","created":"2026-09-01","cited_by_count":3,"area":"agents"},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2603.02345","title":"RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection","created":"2026-03-02","cited_by_count":2,"area":"agents"},{"id":"2605.02584","title":"Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2605.22608","title":"Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2606.11079","title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2607.07989","title":"Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems","created":"2026-07-08","cited_by_count":2,"area":"agents"},{"id":"2607.11698","title":"Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2608.29685","title":"Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2609.04749","title":"DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems","created":"2026-09-04","cited_by_count":2,"area":"lr"},{"id":"2601.17344","title":"The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents","created":"2026-01-24","cited_by_count":1,"area":"agents"},{"id":"2603.13325","title":"Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2604.06633","title":"Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2605.18770","title":"Agentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysis","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2605.20548","title":"What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.21347","title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2605.24140","title":"HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":"lr"},{"id":"2606.07017","title":"The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.12018","title":"MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2606.20662","title":"Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.24626","title":"SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2607.25076","title":"Towards an Agent Operating System - Lessons from Classical and Cloud OS","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2608.02026","title":"HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2608.05573","title":"SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.07583","title":"RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.11967","title":"LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2608.14680","title":"When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2608.29646","title":"Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.02042","title":"Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2609.02057","title":"Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2609.05882","title":"What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2609.35811","title":"Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning","created":"2026-09-20","cited_by_count":1,"area":"agents"},{"id":"2609.40111","title":"Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2601.18588","title":"Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.02378","title":"From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.18968","title":"Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction","created":"2026-02-21","cited_by_count":0,"area":"agents"},{"id":"2604.27358","title":"Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.29511","title":"DynaGraph: Lightweight Multi-Model Interaction Framework via Dynamic Topological Reconfiguration","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01581","title":"Agent System Operations: Categorization, Challenges, and Future Directions","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.10241","title":"Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with ActiveGraph","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.02882","title":"Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference","created":"2026-07-03","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}