{"total":14,"rows":[{"id":"2503.01935","title":"MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents","created":"2025-03-03","cited_by_count":178,"area":"lr"},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2406.00755","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","created":"2024-06-02","cited_by_count":45,"area":"lr"},{"id":"2601.18044","title":"RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models","created":"2026-01-25","cited_by_count":5,"area":"lr"},{"id":"2604.15075","title":"Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2505.13008","title":"Adversarial Reasoning for Repair Based on Inferred Program Intent","created":"2025-05-19","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.25399","title":"CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2504.14038","title":"Flowco: Rethinking Data Analysis in the Age of LLMs","created":"2025-04-18","cited_by_count":1,"area":"lr"},{"id":"2505.12185","title":"EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming","created":"2025-05-18","cited_by_count":1,"area":"lr"},{"id":"2509.05553","title":"Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2602.21681","title":"AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch","created":"2026-02-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}