{"total":94,"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2606.24626","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":"2608.05573","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":"2609.35811","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":"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":"2607.02882","title":"Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.04974","title":"A Comprehensive Study of Implementation Bugs in Multi-modal Agents","created":"2026-07-06","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":"2607.21674","title":"Output Format x Model Identity: Interaction Effects in Single-Round Coding Agent Performance","created":"2026-07-23","cited_by_count":0,"area":"agents"},{"id":"2608.16411","title":"Towards Risk-free AI Agent Deployment","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.30391","title":"Using Grounded Theory for Agent Behavior Analysis at Scale","created":"2026-08-31","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":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.32498","title":"DAAF: From Failure Localization to Editable System Assets in LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33822","title":"Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34649","title":"Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34879","title":"One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37864","title":"AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems","created":"2026-09-29","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":"2610.01207","title":"Dependency-Aware Reward Shaping for Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02994","title":"Sentry: Learning to Recover from LLM Agent Failures at Test Time","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04168","title":"Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents","created":"2026-10-03","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":"2610.10126","title":"Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures","created":"2026-10-07","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":"2610.13105","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"},{"id":"2610.16071","title":"Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17410","title":"Agency as a New Organizing Abstraction for Computer Science","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17613","title":"MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.17633","title":"Executable Prefix Values for Locating Agent Failures","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20518","title":"The Wealth of Agents: Scaling Agentic AI Across Developers","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}