{"version":"1.0","type":"card","id":"e6eb95cd-8fd9-4c64-b3a7-d08205fb4b01","url":"https://stacklist.com/card/e6eb95cd-8fd9-4c64-b3a7-d08205fb4b01","title":"WebArena: Benchmarks for Autonomous Web Agents","source_url":"https://webarena.dev/","note":"WebArena is a comprehensive suite of benchmarks designed to facilitate the development and evaluation of autonomous web agents. It provides tools and metrics to assess the performance and capabilities of these agents in various web environments.","image":{"url":"https://ucarecdn.com/a112d31f-8c39-46f6-9cee-1df10ec05511/","alt":"WebArena: Benchmarks for Autonomous Web Agents","width":1280,"height":800},"stack":{"id":"29e01ac8-6202-4abf-ab14-a0613026186b","title":"AI Agent Evaluation Frameworks and Benchmarks","url":"https://stacklist.com/c/technology/stack/29e01ac8-6202-4abf-ab14-a0613026186b"},"created_at":"2026-07-02T09:48:52.914Z","updated_at":null,"aco":{"summary":"WebArena-x is a suite of benchmarks for building and evaluating autonomous web agents across realistic web environments. The project includes WebArena, WebArena-Infinity, VisualWebArena, and TheAgentCompany, presented at venues such as NeurIPS 2024, ACL 2024, and ICML 2025.","tags":["web-agents","benchmarking","autonomous-agents","multimodal","web-environment","llm-agents","evaluation"],"key_entities":[{"name":"WebArena","type":"technology","confidence":0.98},{"name":"WebArena-Infinity","type":"technology","confidence":0.95},{"name":"VisualWebArena","type":"technology","confidence":0.95},{"name":"TheAgentCompany","type":"technology","confidence":0.93},{"name":"NeurIPS 2024","type":"event","confidence":0.97},{"name":"ACL 2024","type":"event","confidence":0.95},{"name":"ICML 2025","type":"event","confidence":0.95},{"name":"autonomous web agents","type":"concept","confidence":0.96},{"name":"multimodal agents","type":"concept","confidence":0.88}],"classification":"reference","language":"en","confidence":0.85,"provenance":{"model":"claude-opus-4-6","tool":"@stacklist/mcp-server@2.0.0","confidence":0.85,"timestamp":"2026-07-02T09:49:04.878Z"},"token_counts":{"approximate":111,"cl100k":91},"content_hash":"sha256:574a882072eddf2131082fd452470ed10b4144d0fbe8c344eeb1c817e1e7a4c3","acp_version":"0.2","body_available":true,"body_tokens":111,"visibility":"public","agent_accessible":true,"status":"final"},"_links":{"self":"/api/public/card/e6eb95cd-8fd9-4c64-b3a7-d08205fb4b01.json","html":"https://stacklist.com/card/e6eb95cd-8fd9-4c64-b3a7-d08205fb4b01","md":"/api/public/card/e6eb95cd-8fd9-4c64-b3a7-d08205fb4b01.md","stack_json":"/api/public/stack/29e01ac8-6202-4abf-ab14-a0613026186b.json"}}