{"list":"other","total":58,"rows":[{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"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":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320},{"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":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2411.15114","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","created":"2024-11-22","cited_by_count":175},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2410.24024","title":"AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents","created":"2024-10-31","cited_by_count":107},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2310.03903","title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","created":"2023-10-05","cited_by_count":68},{"id":"2412.18174","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","created":"2024-12-24","cited_by_count":64},{"id":"2406.08184","title":"MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents","created":"2024-06-12","cited_by_count":63},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45},{"id":"2407.13943","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","created":"2024-07-18","cited_by_count":45},{"id":"2502.20073","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","created":"2025-02-27","cited_by_count":41},{"id":"1906.09427","title":"Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models","created":"2019-06-22","cited_by_count":36},{"id":"2305.08144","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","created":"2023-05-14","cited_by_count":36},{"id":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32},{"id":"2502.05227","title":"Robotouille: An Asynchronous Planning Benchmark for LLM Agents","created":"2025-02-06","cited_by_count":32},{"id":"2503.07919","title":"BEARCUBS: A benchmark for computer-using web agents","created":"2025-03-10","cited_by_count":31},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27},{"id":"2408.15971","title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","created":"2024-08-28","cited_by_count":26},{"id":"2503.23064","title":"VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models","created":"2025-03-29","cited_by_count":26},{"id":"2211.07615","title":"UGIF: UI Grounded Instruction Following","created":"2022-11-14","cited_by_count":25},{"id":"2503.12349","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","created":"2025-03-16","cited_by_count":24},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24},{"id":"2501.01149","title":"A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation","created":"2025-01-02","cited_by_count":19},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19},{"id":"2403.11905","title":"Tur[k]ingBench: A Challenge Benchmark for Web Agents","created":"2024-03-18","cited_by_count":18},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","cited_by_count":17},{"id":"2504.04808","title":"ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines","created":"2025-04-07","cited_by_count":16},{"id":"2503.20527","title":"StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs","created":"2025-03-26","cited_by_count":14},{"id":"2502.18356","title":"WebGames: Challenging General-Purpose Web-Browsing AI Agents","created":"2025-02-25","cited_by_count":12},{"id":"2504.02623","title":"Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions","created":"2025-04-03","cited_by_count":12},{"id":"2410.06555","title":"ING-VP: MLLMs cannot Play Easy Vision-based Games Yet","created":"2024-10-09","cited_by_count":11},{"id":"2504.06148","title":"V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":11},{"id":"2505.04364","title":"Benchmarking LLMs' Swarm intelligence","created":"2025-05-07","cited_by_count":10},{"id":"2312.12891","title":"MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds","created":"2023-12-20","cited_by_count":6},{"id":"2404.11041","title":"On the Empirical Complexity of Reasoning and Planning in LLMs","created":"2024-04-17","cited_by_count":6},{"id":"2412.13549","title":"EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents","created":"2024-12-18","cited_by_count":6},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6},{"id":"2504.06766","title":"FamilyTool: A Multi-hop Personalized Tool Use Benchmark","created":"2025-04-09","cited_by_count":5}],"next_cursor":null}