{"total":125,"rows":[{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469,"area":"agents"},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93,"area":null},{"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":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2505.19955","title":"MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research","created":"2025-05-26","cited_by_count":64,"area":"agents"},{"id":"2506.15692","title":"MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement","created":"2025-05-27","cited_by_count":58,"area":"agents"},{"id":"2510.16872","title":"DeepAnalyze: Agentic Large Language Models for Autonomous Data Science","created":"2025-10-19","cited_by_count":50,"area":"agents"},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41,"area":"agents"},{"id":"2505.14738","title":"R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science","created":"2025-05-20","cited_by_count":41,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"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":"2506.17335","title":"LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research","created":"2025-06-19","cited_by_count":29,"area":"agents"},{"id":"2504.09702","title":"MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?","created":"2025-04-13","cited_by_count":28,"area":"agents"},{"id":"2501.15427","title":"OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas","created":"2025-01-26","cited_by_count":25,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"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":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2510.01285","title":"LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science","created":"2025-09-30","cited_by_count":15,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2508.02276","title":"CellForge: Agentic Design of Virtual Cell Models","created":"2025-08-04","cited_by_count":13,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2510.23045","title":"A Survey of AI Scientists","created":"2025-10-27","cited_by_count":11,"area":null},{"id":"2601.05930","title":"Can We Predict Before Executing Machine Learning Agents?","created":"2026-01-09","cited_by_count":10,"area":"agents"},{"id":"2507.01599","title":"Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems","created":"2025-07-02","cited_by_count":9,"area":"agents"},{"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":"2510.07307","title":"MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"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":"2505.16100","title":"BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research","created":"2025-05-22","cited_by_count":8,"area":"agents"},{"id":"2506.15695","title":"SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models","created":"2025-05-28","cited_by_count":8,"area":"lr"},{"id":"2508.10177","title":"KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems","created":"2025-08-13","cited_by_count":8,"area":"agents"},{"id":"2603.01712","title":"FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents","created":"2026-03-02","cited_by_count":8,"area":"agents"},{"id":"2605.17373","title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","created":"2026-05-17","cited_by_count":8,"area":"agents"},{"id":"2607.28568","title":"Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering","created":"2026-07-30","cited_by_count":8,"area":"synth"},{"id":"2506.13992","title":"AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"area":"agents"},{"id":"2607.01647","title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2510.05307","title":"When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2510.09517","title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2601.02598","title":"LongDA: Benchmarking LLM Agents for Long-Document Data Analysis","created":"2026-01-05","cited_by_count":6,"area":"agents"},{"id":"2601.13591","title":"DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems","created":"2026-01-20","cited_by_count":6,"area":"agents"},{"id":"2606.05238","title":"DeployBench: Benchmarking LLM Agents for Research Artifact Deployment","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2506.20640","title":"CoMind: Towards Community-Driven Agents for Machine Learning Engineering","created":"2025-06-25","cited_by_count":5,"area":"agents"},{"id":"2605.09698","title":"Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2607.04293","title":"CausalGame: Benchmarking Causal Thinking of LLM Agents in Games","created":"2026-07-05","cited_by_count":5,"area":"lr"},{"id":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"area":"agents"},{"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":"2506.11266","title":"Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling","created":"2025-06-12","cited_by_count":4,"area":"agents"},{"id":"2510.00024","title":"EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis","created":"2025-09-24","cited_by_count":4,"area":"agents"},{"id":"2510.10472","title":"FML-bench: Benchmarking Machine Learning Agents for Scientific Research","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2602.24288","title":"DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2603.22767","title":"Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.12564","title":"Scaling Automatic Research Agents via World Models","created":"2026-08-12","cited_by_count":4,"area":"wm"},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2510.13835","title":"ConDABench: Interactive Evaluation of Language Models for Data Analysis","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2512.00672","title":"ML-Tool-Bench: Tool-Augmented Planning for ML Tasks","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2512.20959","title":"Can Agentic AI Match the Performance of Human Data Scientists?","created":"2025-12-24","cited_by_count":3,"area":"agents"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2601.19578","title":"Yunque DeepResearch Technical Report","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2606.15300","title":"CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?","created":"2026-06-13","cited_by_count":3,"area":null},{"id":"2508.01222","title":"WebDS: An End-to-End Benchmark for Web-based Data Science","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2510.20279","title":"ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2601.23228","title":"Scaling Multiagent Systems with Process Rewards","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2603.19005","title":"AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.09791","title":"Pioneer Agent: Continual Improvement of Small Language Models in Production","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2606.03841","title":"EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.25198","title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","created":"2026-06-23","cited_by_count":2,"area":"agents"},{"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":"2608.10424","title":"Recovering Wasted Compute in Autoresearch Agents","created":"2026-08-11","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2608.26701","title":"Accelerating Scientific Research with Gemini in the Real-World","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2601.06606","title":"CEDAR: Context Engineering for Agentic Data Science","created":"2026-01-10","cited_by_count":1,"area":"agents"},{"id":"2601.15728","title":"Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.01421","title":"SciDER: Scientific Data-centric End-to-end Researcher","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.02729","title":"IndustryCode: A Benchmark for Industry Code Generation","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.14615","title":"An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2607.08093","title":"CausalDS: Benchmarking Causal Reasoning in Data-Science Agents","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2607.11079","title":"Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.15766","title":"Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.10366","title":"DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?","created":"2026-08-11","cited_by_count":1,"area":null}],"next_cursor":"100"}