{"total":21,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2507.09063","title":"SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments","created":"2025-07-11","cited_by_count":18,"area":"agents"},{"id":"2510.25694","title":"Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents","created":"2025-10-29","cited_by_count":18,"area":"agents"},{"id":"2601.03315","title":"Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts","created":"2026-01-06","cited_by_count":13,"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":"2605.25430","title":"CODESKILL: Learning Self-Evolving Skills for Coding Agents","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2606.05238","title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2605.13139","title":"SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle","created":"2026-05-13","cited_by_count":5,"area":"agents"},{"id":"2602.00592","title":"DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2602.09944","title":"Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents","created":"2026-02-10","cited_by_count":2,"area":"agents"},{"id":"2608.03392","title":"Self-Evolving Coding Agents","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2605.26186","title":"SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2607.28591","title":"Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.26546","title":"DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2604.04226","title":"SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web","created":"2026-04-05","cited_by_count":0,"area":"agents"},{"id":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2608.01189","title":"MADE: Belief-Driven Dual-Agent Coordination for Autonomous Model Deployment","created":"2026-08-02","cited_by_count":0,"area":"agents"},{"id":"2609.27571","title":"FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration","created":"2026-09-23","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":"2609.33429","title":"Graph-Guided Repository Environment Construction","created":"2026-09-27","cited_by_count":0,"area":"agents"}],"next_cursor":null}