{"list":"other","total":177,"rows":[{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2407.18901","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","created":"2024-07-26","cited_by_count":401},{"id":"2502.18864","title":"Accelerating scientific discovery with Co-Scientist","created":"2025-02-26","cited_by_count":401},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306},{"id":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292},{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288},{"id":"2503.23278","title":"Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions","created":"2025-03-30","cited_by_count":265},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260},{"id":"2501.09136","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","created":"2025-01-15","cited_by_count":249},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","created":"2024-10-07","cited_by_count":235},{"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":"2402.18679","title":"Data Interpreter: An LLM Agent For Data Science","created":"2024-02-28","cited_by_count":225},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"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":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163},{"id":"2412.19723","title":"OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis","created":"2024-12-27","cited_by_count":163},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","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":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105},{"id":"2408.06327","title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","created":"2024-08-12","cited_by_count":103},{"id":"2403.12881","title":"Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models","created":"2024-03-19","cited_by_count":100},{"id":"2407.01603","title":"A Review of Large Language Models and Autonomous Agents in Chemistry","created":"2024-06-26","cited_by_count":99},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97},{"id":"2407.18416","title":"PersonaGym: Evaluating Persona Agents and LLMs","created":"2024-07-25","cited_by_count":97},{"id":"2410.13185","title":"Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents","created":"2024-10-17","cited_by_count":97},{"id":"2501.10893","title":"Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments","created":"2025-01-18","cited_by_count":95},{"id":"2407.03502","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","created":"2024-07-03","cited_by_count":89},{"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":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86},{"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":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84},{"id":"2312.10003","title":"ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent","created":"2023-12-15","cited_by_count":81},{"id":"2502.15840","title":"Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents","created":"2025-02-20","cited_by_count":80},{"id":"2408.09667","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","created":"2024-08-19","cited_by_count":77},{"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":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71},{"id":"2502.18017","title":"ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents","created":"2025-02-25","cited_by_count":66},{"id":"2503.21248","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","created":"2025-03-27","cited_by_count":66},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65},{"id":"2411.10323","title":"The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use","created":"2024-11-15","cited_by_count":63},{"id":"2502.14321","title":"Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems","created":"2025-02-20","cited_by_count":62},{"id":"2403.03101","title":"KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents","created":"2024-03-05","cited_by_count":61},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59},{"id":"2409.00135","title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","created":"2024-08-29","cited_by_count":57},{"id":"2501.11858","title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","created":"2025-01-21","cited_by_count":57},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57},{"id":"2402.07688","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","created":"2024-02-12","cited_by_count":55},{"id":"2501.10132","title":"ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario","created":"2025-01-17","cited_by_count":55},{"id":"2407.18940","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","created":"2024-07-10","cited_by_count":50},{"id":"2502.01506","title":"TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets","created":"2025-02-03","cited_by_count":48},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45},{"id":"2407.13301","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis","created":"2024-07-18","cited_by_count":43}],"next_cursor":"100"}