{"total":19,"rows":[{"id":"2503.07010","title":"ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation","created":"2025-03-10","cited_by_count":26,"area":"agents"},{"id":"2606.07297","title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","created":"2026-06-05","cited_by_count":21,"area":"agents"},{"id":"2507.00014","title":"SWE-Bench-CL: Continual Learning for Coding Agents","created":"2025-06-13","cited_by_count":14,"area":"agents"},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11,"area":"agents"},{"id":"2503.12029","title":"Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks","created":"2025-03-15","cited_by_count":11,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2603.16124","title":"SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding","created":"2026-03-17","cited_by_count":9,"area":"agents"},{"id":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2412.19770","title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","created":"2024-12-27","cited_by_count":4,"area":"agents"},{"id":"2605.26144","title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","created":"2026-05-22","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2402.02388","title":"Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning","created":"2024-02-04","cited_by_count":2,"area":"agents"},{"id":"2508.12232","title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","created":"2025-08-17","cited_by_count":2,"area":"agents"},{"id":"2607.01425","title":"Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.12161","title":"Token Reduction Is Not Cost Reduction","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2607.24882","title":"Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents","created":"2026-07-27","cited_by_count":2,"area":"agents"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2606.08151","title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2607.15948","title":"TARS: A Theory-of-Mind Agent for Personalized In-IDE Code Comprehension","created":"2026-07-17","cited_by_count":0,"area":"agents"}],"next_cursor":null}