{"total":104,"rows":[{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2510.11977","title":"Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation","created":"2025-10-13","cited_by_count":92,"area":"agents"},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"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":"2509.13782","title":"Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis","created":"2025-09-17","cited_by_count":33,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2509.02360","title":"When Agents go Astray: Course-Correcting SWE Agents with PRMs","created":"2025-09-02","cited_by_count":28,"area":"agents"},{"id":"2512.02393","title":"Process-Centric Analysis of Agentic Software Systems","created":"2025-12-02","cited_by_count":24,"area":"agents"},{"id":"2512.06749","title":"DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems","created":"2025-12-07","cited_by_count":24,"area":"agents"},{"id":"2509.14295","title":"Aegis: Automated Error Generation and Attribution for Multi-Agent Systems","created":"2025-09-17","cited_by_count":22,"area":"agents"},{"id":"2509.06822","title":"RAFFLES: Reasoning-based Attribution of Faults for LLM Systems","created":"2025-09-08","cited_by_count":21,"area":"lr"},{"id":"2509.08682","title":"Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference","created":"2025-09-10","cited_by_count":18,"area":null},{"id":"2602.17037","title":"Wink: Recovering from Misbehaviors in Coding Agents","created":"2026-02-19","cited_by_count":15,"area":"agents"},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2507.11277","title":"Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems","created":"2025-07-15","cited_by_count":12,"area":"agents"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2510.08847","title":"What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment","created":"2025-10-09","cited_by_count":8,"area":"agents"},{"id":"2607.12747","title":"Tracing Agentic Failure from the Flow of Success","created":"2026-07-14","cited_by_count":8,"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":"2608.14905","title":"How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks","created":"2026-08-14","cited_by_count":8,"area":"agents"},{"id":"2601.00481","title":"MAESTRO: Multi-Agent Evaluation Suite for Testing, Reliability, and Observability","created":"2026-01-01","cited_by_count":7,"area":"agents"},{"id":"2603.29848","title":"AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems","created":"2026-02-18","cited_by_count":7,"area":"agents"},{"id":"2606.08091","title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","created":"2026-06-06","cited_by_count":7,"area":"agents"},{"id":"2606.09071","title":"REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces","created":"2026-06-08","cited_by_count":7,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"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":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2603.21522","title":"Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation","created":"2026-03-23","cited_by_count":6,"area":"lr"},{"id":"2603.23806","title":"Willful Disobedience: Automatically Detecting Failures in Agentic Traces","created":"2026-03-25","cited_by_count":6,"area":"agents"},{"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":"2606.02060","title":"Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories","created":"2026-06-01","cited_by_count":6,"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":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"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":"2606.27409","title":"Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement","created":"2026-06-25","cited_by_count":4,"area":"agents"},{"id":"2607.16387","title":"Fantastic Adaptive Taxonomies and How to Use Them","created":"2026-07-17","cited_by_count":4,"area":null},{"id":"2601.17915","title":"Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2603.24629","title":"Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models","created":"2026-03-25","cited_by_count":3,"area":"agents"},{"id":"2606.03467","title":"StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems","created":"2026-06-02","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","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":"2608.24271","title":"Observability and Fault Injection for LLM-Based Multi-Agent Systems in Software Engineering","created":"2026-08-25","cited_by_count":3,"area":"agents"},{"id":"2608.25920","title":"Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems","created":"2026-08-26","cited_by_count":3,"area":"lr"},{"id":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"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":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2602.04640","title":"Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents","created":"2026-02-04","cited_by_count":2,"area":"agents"},{"id":"2603.29678","title":"View-oriented Conversation Compiler for Agent Trace Analysis","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.22608","title":"Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2606.14805","title":"Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2607.18816","title":"AgentTrails: Towards Trust and Reuse for Agentic Tasks","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2608.05212","title":"SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.06701","title":"Online Monitoring and Corrective Steering of Programming Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2608.15242","title":"LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"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":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.17699","title":"SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agents","created":"2026-04-20","cited_by_count":1,"area":"agents"},{"id":"2604.23455","title":"CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend","created":"2026-04-25","cited_by_count":1,"area":"agents"},{"id":"2605.14865","title":"Holistic Evaluation and Failure Diagnosis of AI Agents","created":"2026-05-14","cited_by_count":1,"area":null},{"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":"2606.24626","title":"SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2608.00718","title":"Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"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":"2608.14680","title":"When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.29646","title":"Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.40111","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":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2610.01256","title":"DeFA: Dependency-Guided Failure Attribution for LLM Agents","created":"2026-10-01","cited_by_count":1,"area":"agents"},{"id":"2510.17874","title":"Repairing Tool Calls Using Post-tool Execution Reflection and RAG","created":"2025-10-17","cited_by_count":0,"area":"agents"},{"id":"2605.24733","title":"StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering","created":"2026-05-23","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":"2606.21627","title":"Counsel: A Meta-Evaluation Dataset for Agentic Tasks","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2606.26118","title":"The Open Source Economic Index of AI Adoption and Capability","created":"2026-05-23","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"},{"id":"2607.13920","title":"DeepStress: Stress-Testing Deep Search Agents","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.13667","title":"Second Thought: Reasoning in Parallel as LLM Agents Act and Observe","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.18575","title":"Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2609.01466","title":"Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.06063","title":"Explaining AI Agents Through Execution Traces","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.06835","title":"Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.13463","title":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.20625","title":"Chronicle: Cut-Point Replay for Regression Testing of LLM Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.23808","title":"FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32495","title":"Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32776","title":"On the Behavioral Traits of LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33676","title":"Auditing Agent Actions through Query-Conditioned Attribution","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33717","title":"Self-Designed Evaluators and Warm Memory for Long-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.36556","title":"MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39957","title":"Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01161","title":"My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11655","title":"Harness Evolution Hits a Ceiling: When Weight Training Should Begin","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12360","title":"Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13105","title":"Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}