{"total":17,"rows":[{"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":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2603.04177","title":"CodeTaste: Can LLMs Generate Human-Level Code Refactorings?","created":"2026-03-04","cited_by_count":8,"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":"2605.08366","title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","created":"2026-05-08","cited_by_count":6,"area":"agents"},{"id":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2602.23668","title":"PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents","created":"2026-02-27","cited_by_count":2,"area":"agents"},{"id":"2605.20244","title":"Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2601.00482","title":"Multi-Agent Coordinated Rename Refactoring","created":"2026-01-01","cited_by_count":0,"area":"agents"},{"id":"2603.00601","title":"Theory of Code Space: Do Code Agents Understand Software Architecture?","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2605.08468","title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2606.05574","title":"SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2609.01271","title":"What Does an Agentic Software Engineering Benchmark Measure? Profiling Task Demands and Agent Behaviour Beyond What Category Labels Reveal","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.04898","title":"RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2610.17616","title":"StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}