{"total":116,"rows":[{"id":"2512.18746","title":"MemEvolve: Meta-Evolution of Agent Memory Systems","created":"2025-12-21","cited_by_count":95,"area":"agents"},{"id":"2604.08377","title":"SkillClaw: Let Skills Evolve Collectively with Agentic Evolver","created":"2026-04-09","cited_by_count":81,"area":"agents"},{"id":"2509.26603","title":"DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively","created":"2025-09-30","cited_by_count":63,"area":null},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2603.17187","title":"MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild","created":"2026-03-17","cited_by_count":37,"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":"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":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"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":"2603.25001","title":"Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation","created":"2026-03-26","cited_by_count":24,"area":"lr"},{"id":"2602.23701","title":"From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems","created":"2026-02-27","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":"2601.15778","title":"Agentic Confidence Calibration","created":"2026-01-22","cited_by_count":15,"area":"agents"},{"id":"2606.09863","title":"From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents","created":"2026-06-01","cited_by_count":15,"area":"agents"},{"id":"2606.19659","title":"SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation","created":"2026-06-17","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":"2510.26585","title":"Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems","created":"2025-10-30","cited_by_count":12,"area":"agents"},{"id":"2605.10913","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"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":"2512.01948","title":"How Far Are We from Genuinely Useful Deep Research Agents?","created":"2025-12-01","cited_by_count":11,"area":"agents"},{"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":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2509.23735","title":"Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows","created":"2025-09-28","cited_by_count":10,"area":"agents"},{"id":"2510.15624","title":"Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation","created":"2025-10-17","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":"2607.12747","title":"Tracing Agentic Failure from the Flow of Success","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"id":"2510.00507","title":"Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs","created":"2025-10-01","cited_by_count":7,"area":"mllm"},{"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":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"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":"2605.07509","title":"MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals","created":"2026-05-08","cited_by_count":6,"area":"agents"},{"id":"2605.14859","title":"Do Coding Agents Understand Least-Privilege Authorization?","created":"2026-05-14","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":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2604.10290","title":"AI Organizations are More Effective but Less Aligned than Individual Agents","created":"2026-04-11","cited_by_count":5,"area":null},{"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":"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":"2604.17658","title":"Towards Self-Improving Error Diagnosis in Multi-Agent Systems","created":"2026-04-19","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":"2605.29790","title":"Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2510.06800","title":"FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline","created":"2025-10-08","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":"2604.23505","title":"Uncertainty Propagation in LLM-Based Systems","created":"2026-04-26","cited_by_count":3,"area":null},{"id":"2605.17169","title":"Responsible Agentic AI Requires Explicit Provenance","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"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":"2605.23414","title":"When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems","created":"2026-05-22","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":"2606.17838","title":"Environment-Grounded Automated Prompt Optimization for LLM Game Agents","created":"2026-06-16","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":"2609.08572","title":"AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2602.23258","title":"MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.29678","title":"View-oriented Conversation Compiler for Agent Trace Analysis","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.03354","title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2605.17439","title":"DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.23956","title":"QUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems","created":"2026-05-11","cited_by_count":2,"area":null},{"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":"2607.07989","title":"Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems","created":"2026-07-08","cited_by_count":2,"area":"agents"},{"id":"2607.18816","title":"AgentTrails: Towards Trust and Reuse for Agentic Tasks","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"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":"2609.06972","title":"AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories","created":"2026-09-07","cited_by_count":2,"area":"agents"},{"id":"2609.16057","title":"OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning","created":"2026-09-13","cited_by_count":2,"area":"mllm"},{"id":"2609.18304","title":"Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2601.20538","title":"Interpreting Emergent Extreme Events in Multi-Agent Systems","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2603.00309","title":"DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths","created":"2026-02-27","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":"2605.24197","title":"A Sober Look at Agentic Misalignment in Automated Workflows","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2607.07702","title":"From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization","created":"2026-07-08","cited_by_count":1,"area":"agents"},{"id":"2607.29055","title":"Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search","created":"2026-07-31","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":"2608.07583","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":"2608.07899","title":"TelemetrySuffBench: Is Agent Telemetry Sufficient for Failure-Origin Diagnosis?","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2608.10646","title":"ASCon: A Direction-Aware Reciprocal Agent--Step Contextualization Model for Failure Attribution in Multi-Agent Systems","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.24361","title":"Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems","created":"2026-08-25","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":"2609.10548","title":"When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems","created":"2026-06-25","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":"2604.22820","title":"Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.11404","title":"Attributing Emergence in Million-Agent Systems","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.25376","title":"KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition","created":"2026-05-25","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":"2606.06708","title":"Signal-Driven Observation for Long-Horizon Web Agents","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"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":"2607.13884","title":"Experience Memory Graph: One-Shot Error Correction for Agents","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"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":"2608.22160","title":"AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.22960","title":"What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.28067","title":"SEPO: Evidence-Grounded Prompt Optimization via Structural Editing","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29228","title":"Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.02371","title":"Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.10892","title":"DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents","created":"2026-09-09","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":"2609.25804","title":"The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.30725","title":"Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents","created":"2026-09-25","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}],"next_cursor":"100"}