{"total":52,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2411.15114","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","created":"2024-11-22","cited_by_count":175,"area":"agents"},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89,"area":"agents"},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2502.11705","title":"LLM Agents Making Agent Tools","created":"2025-02-17","cited_by_count":48,"area":"agents"},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21,"area":"agents"},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"id":"2506.22598","title":"RExBench: Can coding agents autonomously implement AI research extensions?","created":"2025-06-27","cited_by_count":18,"area":"agents"},{"id":"2505.13291","title":"TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents","created":"2025-05-19","cited_by_count":15,"area":"agents"},{"id":"2506.02064","title":"The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims","created":"2025-06-01","cited_by_count":14,"area":"agents"},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2503.01424","title":"From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems","created":"2025-03-03","cited_by_count":8,"area":null},{"id":"2605.16616","title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2608.19799","title":"SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?","created":"2026-08-20","cited_by_count":6,"area":"agents"},{"id":"2410.20445","title":"TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration","created":"2024-10-27","cited_by_count":5,"area":"agents"},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2509.20374","title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2506.13109","title":"Leveraging In-Context Learning for Language Model Agents","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2605.08941","title":"MDGYM: Benchmarking AI Agents on Molecular Simulations","created":"2026-05-09","cited_by_count":4,"area":"agents"},{"id":"2603.06739","title":"ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2509.01619","title":"Throttling Web Agents Using Reasoning Gates","created":"2025-09-01","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":"2603.30038","title":"Benchmarking PhD-Level Coding in 3D Geometric Computer Vision","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2507.15736","title":"IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2605.26186","title":"SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2503.21138","title":"A Computational Theory for Efficient Mini Agent Evaluation with Causal Guarantees","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2512.01089","title":"CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents","created":"2025-11-30","cited_by_count":0,"area":"agents"},{"id":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.16902","title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2608.27334","title":"BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.03416","title":"Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"id":"2609.07362","title":"BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2610.00636","title":"CompMat-Bench: Benchmarking AI Agents for Computational Materials Science","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}