{"url":"/task/autonomous-web-navigation","name":"Autonomous Web Navigation","slug":"autonomous-web-navigation","description_markdown":"Evaluating agents on the task of navigating on the Web to solve a user given task/instruction","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":9,"papers_with_code":4,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/autonomous-navigation","name":"Autonomous Navigation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":9,"items":[{"url":"/paper/real-benchmarking-autonomous-agents-on","title":"REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites","date":"2025-04-15","arxiv_id":"2504.11543","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/magma-a-foundation-model-for-multimodal-ai","title":"Magma: A Foundation Model for Multimodal AI Agents","date":"2025-02-18","arxiv_id":"2502.13130","repositories_listed":2,"syntology":{"n":16,"n_ran":2,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/agent-e-from-autonomous-web-navigation-to","title":"Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems","date":"2024-07-17","arxiv_id":"2407.13032","repositories_listed":2,"syntology":null},{"url":"/paper/st-webagentbench-a-benchmark-for-evaluating","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","date":"2024-10-09","arxiv_id":"2410.06703","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}