{"total":13,"rows":[{"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":"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":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2607.29175","title":"Execution-First Synthetic Tool-Use Trace Generation for LLM Agents","created":"2026-07-31","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":"2607.24604","title":"Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2608.16630","title":"The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2609.12742","title":"Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents","created":"2026-09-11","cited_by_count":1,"area":"agents"},{"id":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2607.28871","title":"Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2609.17394","title":"Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.24928","title":"Trajectory-Aware Benchmark Subset Selection for Cost-Efficient Software Engineering Agent Regression Testing","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2610.13356","title":"SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}