{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"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":"2309.17288","title":"AutoAgents: A Framework for Automatic Agent Generation","created":"2023-09-29","cited_by_count":216},{"id":"2404.07738","title":"ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models","created":"2024-04-11","cited_by_count":210},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148},{"id":"2312.00164","title":"Towards Accurate Differential Diagnosis with Large Language Models","created":"2023-11-30","cited_by_count":116},{"id":"2402.06664","title":"LLM Agents can Autonomously Hack Websites","created":"2024-02-06","cited_by_count":109},{"id":"2403.01038","title":"AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks","created":"2024-03-02","cited_by_count":96},{"id":"2407.12821","title":"AutoFlow: Automated Workflow Generation for Large Language Model Agents","created":"2024-07-01","cited_by_count":83},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2408.01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","created":"2024-08-02","cited_by_count":58},{"id":"2312.17025","title":"Experiential Co-Learning of Software-Developing Agents","created":"2023-12-28","cited_by_count":57},{"id":"2404.17605","title":"Autonomous LLM-driven research from data to human-verifiable research papers","created":"2024-04-24","cited_by_count":53},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52},{"id":"2407.18940","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","created":"2024-07-10","cited_by_count":50},{"id":"2411.00114","title":"Project Sid: Many-agent simulations toward AI civilization","created":"2024-10-31","cited_by_count":49},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48},{"id":"2405.06682","title":"Self-Reflection in LLM Agents: Effects on Problem-Solving Performance","created":"2024-05-05","cited_by_count":39},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30},{"id":"2408.15545","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","created":"2024-08-28","cited_by_count":29},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28},{"id":"2411.03562","title":"Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance","created":"2024-11-05","cited_by_count":25},{"id":"2401.13481","title":"How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experiment","created":"2024-01-24","cited_by_count":22},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22},{"id":"2406.06357","title":"MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows","created":"2024-06-10","cited_by_count":19},{"id":"2411.03743","title":"Automating Exploratory Proteomics Research via Language Models","created":"2024-11-06","cited_by_count":11},{"id":"2407.00466","title":"BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science","created":"2024-06-29","cited_by_count":10},{"id":"2407.16931","title":"ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering","created":"2024-07-24","cited_by_count":6},{"id":"2407.16604","title":"Shared Imagination: LLMs Hallucinate Alike","created":"2024-07-23","cited_by_count":5},{"id":"2406.13049","title":"Assessing AI-Generated vs. Human-Authored Spear Phishing SMS Attacks: An Empirical Study","created":"2024-06-18","cited_by_count":1}],"next_cursor":null}