{"list":"other","total":52,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"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":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"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":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"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":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2504.07079","title":"SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills","created":"2025-04-09","cited_by_count":192},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158},{"id":"2510.04374","title":"GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks","created":"2025-10-05","cited_by_count":158},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111},{"id":"2407.01725","title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","created":"2024-07-01","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":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100},{"id":"2503.04761","title":"Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations","created":"2025-02-11","cited_by_count":96},{"id":"2410.15164","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","created":"2024-10-19","cited_by_count":81},{"id":"2411.02305","title":"CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments","created":"2024-11-04","cited_by_count":71},{"id":"2407.19056","title":"OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation","created":"2024-07-26","cited_by_count":70},{"id":"2404.09992","title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","created":"2024-04-15","cited_by_count":55},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48},{"id":"2601.18137","title":"DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints","created":"2026-01-26","cited_by_count":46},{"id":"2506.06576","title":"Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce","created":"2025-06-06","cited_by_count":38},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37},{"id":"2506.01952","title":"WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks","created":"2025-06-02","cited_by_count":30},{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19},{"id":"2410.12851","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","created":"2024-10-10","cited_by_count":17},{"id":"2510.27287","title":"Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments","created":"2025-10-31","cited_by_count":17},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15},{"id":"2404.05337","title":"Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level","created":"2024-04-08","cited_by_count":11},{"id":"2505.19662","title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","created":"2025-05-26","cited_by_count":6}],"next_cursor":null}