{"total":16,"rows":[{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"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":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2603.27296","title":"A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2607.02440","title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2604.19827","title":"More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.21964","title":"Repo2Skill-Evo: Repository Skills Go Stale in Silence","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.07832","title":"Harness Engineering for Software Engineering via Modular Executable Dev-Primitives","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}