{"total":17,"rows":[{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"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":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"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":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2510.04852","title":"FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration","created":"2025-10-06","cited_by_count":5,"area":"agents"},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2605.06125","title":"Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2607.09123","title":"ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2510.07147","title":"A Multi-Agent Framework for Stateful Inference-Time Search","created":"2025-10-08","cited_by_count":0,"area":"agents"},{"id":"2609.05978","title":"VibeCheck: Assessing the Quality of LLM-Generated Unit Tests: A Multi-agent Empirical Study across Heterogeneous Repositories","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.16870","title":"SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}