{"total":24,"rows":[{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"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":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6,"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":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.10646","title":"CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2603.26137","title":"ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation","created":"2026-03-27","cited_by_count":3,"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":"2606.30963","title":"Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2512.25065","title":"Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search","created":"2025-12-31","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":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","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":"2507.13499","title":"AI-Assisted Fixes to Code Review Comments at Scale","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2602.13921","title":"GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.24946","title":"MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Development","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.26100","title":"Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models","created":"2026-05-25","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":"2608.14838","title":"The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context","created":"2026-08-14","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}],"next_cursor":null}