{"total":22,"rows":[{"id":"2410.20424","title":"AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions","created":"2024-10-27","cited_by_count":70,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2410.22394","title":"AAAR-1.0: Assessing AI's Potential to Assist Research","created":"2024-10-29","cited_by_count":24,"area":null},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2605.08678","title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","created":"2026-05-09","cited_by_count":17,"area":null},{"id":"2506.02672","title":"EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2510.12367","title":"LLM-REVal: Can We Trust LLM Reviewers Yet?","created":"2025-10-14","cited_by_count":9,"area":null},{"id":"2403.04791","title":"LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2605.09636","title":"PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation","created":"2026-05-10","cited_by_count":8,"area":null},{"id":"2505.12331","title":"OSS-Bench: Benchmark Generator for Coding LLMs","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2607.25090","title":"Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2508.04279","title":"Mockingbird: How does LLM perform in general machine learning tasks?","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2601.21410","title":"Learning When to Trust LLM Priors: A Validated Framework for Semantic Prior Integration","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.12634","title":"RPRA: Predicting an LLM-Judge for Efficient but Performant Inference","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2609.02272","title":"PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}