{"total":19,"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":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2512.17419","title":"SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories","created":"2025-12-19","cited_by_count":28,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"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":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2509.16749","title":"Evaluating LLM Generated Detection Rules in Cybersecurity","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.37233","title":"DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04658","title":"RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}