{"total":15,"rows":[{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2609.04061","title":"When Models Edit Too Much: On the Fidelity of Minimal Code Edits","created":"2026-09-03","cited_by_count":3,"area":null},{"id":"2606.25530","title":"Evaluating LLMs on Real-World Software Performance Optimization","created":"2026-06-24","cited_by_count":2,"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":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.05137","title":"EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.15815","title":"BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.01764","title":"Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.14839","title":"Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.13563","title":"Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}