{"list":"other","total":63,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386},{"id":"2310.03302","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","created":"2023-10-05","cited_by_count":366},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163},{"id":"2412.05467","title":"The BrowserGym Ecosystem for Web Agent Research","created":"2024-12-06","cited_by_count":161},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130},{"id":"2402.17453","title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning","created":"2024-02-27","cited_by_count":125},{"id":"2409.07703","title":"DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?","created":"2024-09-12","cited_by_count":125},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124},{"id":"1907.08322","title":"MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III","created":"2019-07-19","cited_by_count":122},{"id":"2406.04151","title":"AgentGym: Evolving Large Language Model-based Agents across Diverse Environments","created":"2024-06-06","cited_by_count":120},{"id":"2505.20286","title":"Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution","created":"2025-05-26","cited_by_count":116},{"id":"2407.02483","title":"MMedAgent: Learning to Use Medical Tools with Multi-modal Agent","created":"2024-07-02","cited_by_count":109},{"id":"2307.02028","title":"EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models","created":"2023-07-05","cited_by_count":105},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85},{"id":"1908.01839","title":"Text-to-SQL Generation for Question Answering on Electronic Medical Records","created":"2019-07-28","cited_by_count":77},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70},{"id":"2311.09835","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","created":"2023-11-16","cited_by_count":65},{"id":"2412.15701","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","created":"2024-12-20","cited_by_count":65},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57},{"id":"2502.11435","title":"SMART: Self-Aware Agent for Tool Overuse Mitigation","created":"2025-02-17","cited_by_count":52},{"id":"2301.07695","title":"EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records","created":"2023-01-16","cited_by_count":45},{"id":"2502.04780","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","created":"2025-02-07","cited_by_count":44},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43},{"id":"2402.13225","title":"AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning","created":"2024-02-20","cited_by_count":33},{"id":"2402.17168","title":"Benchmarking Data Science Agents","created":"2024-02-27","cited_by_count":30},{"id":"2303.12961","title":"The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs","created":"2023-03-22","cited_by_count":29},{"id":"2505.12371","title":"MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks","created":"2025-05-18","cited_by_count":29},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25},{"id":"2308.14120","title":"Large Language Models Streamline Automated Machine Learning for Clinical Studies","created":"2023-08-27","cited_by_count":24},{"id":"2410.17657","title":"ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents","created":"2024-10-23","cited_by_count":20},{"id":"2505.16100","title":"BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research","created":"2025-05-22","cited_by_count":8},{"id":"2406.00019","title":"EHR-SeqSQL : A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records","created":"2024-05-23","cited_by_count":5},{"id":"2406.16341","title":"EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records","created":"2024-06-24","cited_by_count":3}],"next_cursor":null}