{"total":45,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"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":"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":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"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":"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":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"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":"2510.23045","title":"A Survey of AI Scientists","created":"2025-10-27","cited_by_count":11,"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":"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":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null},{"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":"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":"2601.19578","title":"Yunque DeepResearch Technical Report","created":"2026-01-27","cited_by_count":3,"area":null},{"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":"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":"2608.26701","title":"Accelerating Scientific Research with Gemini in the Real-World","created":"2026-08-27","cited_by_count":2,"area":null},{"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":"2604.14615","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":"2607.11079","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},{"id":"2606.11176","title":"Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.22977","title":"StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.26757","title":"DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01982","title":"Benchmarking Language Models for Statistical Problem Formulation","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},{"id":"2609.34228","title":"SleuthBench: Benchmarking Statistical LLM Evaluation Using Tabular Hidden Signals","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02122","title":"Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.14700","title":"DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16175","title":"ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}