{"total":12,"rows":[{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2506.11058","title":"Refactoring Codebases through Library Design","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2604.11072","title":"Hodoscope: Unsupervised Monitoring for AI Misbehaviors","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2608.09277","title":"P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.21405","title":"Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2609.36730","title":"Can Agents Design Libraries for Agents?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}