{"total":20,"rows":[{"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":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","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":"2608.03222","title":"Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks","created":"2026-08-04","cited_by_count":5,"area":"agents"},{"id":"2608.18398","title":"LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents","created":"2026-08-19","cited_by_count":5,"area":"agents"},{"id":"2604.12147","title":"From Plan to Action: How Well Do Agents Follow the Plan?","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2604.02665","title":"AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2606.22110","title":"TraceView: Interactive Visualization of Agentic Program Repair Trajectories","created":"2026-06-20","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":"2608.06701","title":"Online Monitoring and Corrective Steering of Programming Agents","created":"2026-08-07","cited_by_count":2,"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":"2607.16740","title":"Agentic Code Review in the Terminal: A Trajectory-Level Analysis of Behavior, Cost, and Human-Alignment","created":"2026-07-18","cited_by_count":1,"area":"agents"},{"id":"2607.22807","title":"The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.17195","title":"Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2607.01808","title":"Archer: Towards Agentic Review for Compiler Optimizations","created":"2026-07-02","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":"2608.20597","title":"Testing and Evaluation of Agentic AI Systems In Military Command and Control","created":"2026-08-20","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":"2609.39957","title":"Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}