{"list":"other","total":74,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2506.13131","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","created":"2025-06-16","cited_by_count":867},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2307.14984","title":"S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents","created":"2023-07-27","cited_by_count":233},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"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},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168},{"id":"2504.11703","title":"Progent: Securing AI Agents with Privilege Control","created":"2025-04-16","cited_by_count":141},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137},{"id":"2508.16153","title":"Memento: Fine-tuning LLM Agents without Fine-tuning LLMs","created":"2025-08-22","cited_by_count":127},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126},{"id":"2406.06608","title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","created":"2024-06-06","cited_by_count":121},{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120},{"id":"2411.04890","title":"GUI Agents with Foundation Models: A Comprehensive Survey","created":"2024-11-07","cited_by_count":111},{"id":"2505.02279","title":"A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)","created":"2025-05-04","cited_by_count":101},{"id":"2503.24047","title":"Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents","created":"2025-03-31","cited_by_count":98},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86},{"id":"2503.08979","title":"Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions","created":"2025-03-12","cited_by_count":77},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72},{"id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60},{"id":"2503.10970","title":"TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools","created":"2025-03-14","cited_by_count":59},{"id":"2504.10157","title":"SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users","created":"2025-04-14","cited_by_count":55},{"id":"2503.19213","title":"A Survey of Large Language Model Agents for Question Answering","created":"2025-03-24","cited_by_count":48},{"id":"2411.05025","title":"LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions","created":"2024-10-30","cited_by_count":47},{"id":"2507.05241","title":"SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?","created":"2025-07-07","cited_by_count":47},{"id":"2408.00818","title":"Y Social: an LLM-powered Social Media Digital Twin","created":"2024-08-01","cited_by_count":44},{"id":"2504.13171","title":"Sleep-time Compute: Beyond Inference Scaling at Test-time","created":"2025-04-17","cited_by_count":43},{"id":"2405.14767","title":"FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models","created":"2024-05-23","cited_by_count":40},{"id":"2503.22678","title":"Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions","created":"2025-03-28","cited_by_count":40},{"id":"2407.21320","title":"MetaOpenFOAM: an LLM-based multi-agent framework for CFD","created":"2024-07-31","cited_by_count":39},{"id":"2202.08994","title":"REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening","created":"2022-02-18","cited_by_count":38},{"id":"2312.13010","title":"AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation","created":"2023-12-20","cited_by_count":35},{"id":"2410.20746","title":"ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents","created":"2024-10-28","cited_by_count":35},{"id":"2501.07531","title":"Evaluating Agent-based Program Repair at Google","created":"2025-01-13","cited_by_count":35},{"id":"2506.01056","title":"MCP-Zero: Active Tool Discovery for Autonomous LLM Agents","created":"2025-06-01","cited_by_count":33},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32},{"id":"2506.19923","title":"Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs","created":"2025-06-24","cited_by_count":31},{"id":"2502.14776","title":"SurveyX: Academic Survey Automation via Large Language Models","created":"2025-02-20","cited_by_count":29},{"id":"2408.08631","title":"Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks","created":"2024-08-16","cited_by_count":28},{"id":"2311.10776","title":"Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis","created":"2023-11-16","cited_by_count":25},{"id":"2406.19966","title":"Simulating Financial Market via Large Language Model based Agents","created":"2024-06-28","cited_by_count":25},{"id":"2504.16918","title":"OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents","created":"2025-04-23","cited_by_count":22},{"id":"2503.22164","title":"PharmAgents: Building a Virtual Pharma with Large Language Model Agents","created":"2025-03-28","cited_by_count":21},{"id":"2405.07761","title":"LLM4ED: Large Language Models for Automatic Equation Discovery","created":"2024-05-13","cited_by_count":14},{"id":"2411.18892","title":"A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges","created":"2024-11-28","cited_by_count":13},{"id":"2502.00498","title":"MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing","created":"2025-02-01","cited_by_count":13},{"id":"2503.21422","title":"From Deep Learning to LLMs: A survey of AI in Quantitative Investment","created":"2025-03-27","cited_by_count":9},{"id":"2504.03424","title":"The AI Cosmologist I: An Agentic System for Automated Data Analysis","created":"2025-04-04","cited_by_count":9},{"id":"2501.06314","title":"BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems","created":"2025-01-10","cited_by_count":8},{"id":"2503.23170","title":"AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data","created":"2025-03-29","cited_by_count":8},{"id":"2504.17669","title":"Towards a HIPAA Compliant Agentic AI System in Healthcare","created":"2025-04-24","cited_by_count":8},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8},{"id":"2504.07634","title":"Agent That Debugs: Dynamic State-Guided Vulnerability Repair","created":"2025-04-10","cited_by_count":7},{"id":"2503.16547","title":"Empowering Medical Multi-Agents with Clinical Consultation Flow for Dynamic Diagnosis","created":"2025-03-19","cited_by_count":5},{"id":"2408.13378","title":"DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment","created":"2024-08-23","cited_by_count":4},{"id":"2502.14327","title":"ChemHTS: Hierarchical Tool Stacking for Enhancing Chemical Agents","created":"2025-02-20","cited_by_count":4},{"id":"2506.06574","title":"The Optimization Paradox in Clinical AI Multi-Agent Systems","created":"2025-06-06","cited_by_count":4},{"id":"2407.09977","title":"Mitigating Interpretation Bias in Rock Records with Large Language Models: Insights from Paleoenvironmental Analysis","created":"2024-05-17","cited_by_count":1}],"next_cursor":null}