EvoBrowseComp is a search agent benchmark of 400 English and 400 Chinese contamination-free complex questions synthesized via live-web traversal.</p>\n","updatedAt":"2026-06-12T03:21:47.488Z","author":{"_id":"6051e3f145db307eddc0c962","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676443438507-6051e3f145db307eddc0c962.jpeg","fullname":"Jiaan Wang","name":"Krystalan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":14,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6716024279594421},"editors":["Krystalan"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1676443438507-6051e3f145db307eddc0c962.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.13120","authors":[{"_id":"6a2b7ad24957fcdd3aac06dc","name":"Yunhan Wang","hidden":false},{"_id":"6a2b7ad24957fcdd3aac06dd","user":{"_id":"6051e3f145db307eddc0c962","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676443438507-6051e3f145db307eddc0c962.jpeg","isPro":false,"fullname":"Jiaan Wang","user":"Krystalan","type":"user","name":"Krystalan"},"name":"Jiaan Wang","status":"claimed_verified","statusLastChangedAt":"2026-06-12T06:56:28.803Z","hidden":false},{"_id":"6a2b7ad24957fcdd3aac06de","name":"Lianzhe Huang","hidden":false},{"_id":"6a2b7ad24957fcdd3aac06df","name":"Xianfeng Zeng","hidden":false},{"_id":"6a2b7ad24957fcdd3aac06e0","name":"Fandong Meng","hidden":false}],"publishedAt":"2026-06-11T00:00:00.000Z","submittedOnDailyAt":"2026-06-12T00:00:00.000Z","title":"EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge","submittedOnDailyBy":{"_id":"6051e3f145db307eddc0c962","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676443438507-6051e3f145db307eddc0c962.jpeg","isPro":false,"fullname":"Jiaan Wang","user":"Krystalan","type":"user","name":"Krystalan"},"summary":"Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely on static knowledge, making them vulnerable to test-set contamination and parametric memorization. Consequently, models can achieve high scores through fact recall rather than genuine retrieval, obscuring true browsing competence via reasoning shortcuts.\n In this paper, we introduce EvoBrowseComp, an evolving benchmark of 400 English and 400 Chinese contamination-free complex questions synthesized via live-web traversal. To collect these questions, we design a three-agent collaborative framework: (1) a QA synthesis agent that retrieves fresh knowledge from the live web to synthesize QA pairs; (2) an information filtering agent that filters retrieved knowledge in terms of credibility and popularity to block parametric shortcuts; and (3) a high-level guidance agent that formalizes questions into reasoning graphs to reduce logical redundancy and shortcuts in synthesized QA pairs. Because the framework supports fully automated synthesis, EvoBrowseComp can be regularly updated to prevent data contamination and maintain temporal freshness. Extensive experiments confirm its great difficulty, requiring broad horizontal search. It establishes a scalable paradigm for auto-updatable, high-difficulty benchmarking that keeps pace with both evolving world knowledge and advancing agent capabilities.","upvotes":3,"discussionId":"6a2b7ad24957fcdd3aac06e1","projectPage":"https://huggingface.co/datasets/Krystalan/EvoBrowseComp","ai_summary":"EvoBrowseComp is an evolving benchmark with 800 contamination-free questions synthesized through a three-agent framework that ensures temporal freshness and prevents parametric memorization in search agent evaluation.","ai_keywords":["search agents","large language models","browsecomp","contamination-free","live-web traversal","QA synthesis agent","information filtering agent","high-level guidance agent","reasoning graphs","automated synthesis","temporal freshness","parametric memorization"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6051e3f145db307eddc0c962","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1676443438507-6051e3f145db307eddc0c962.jpeg","isPro":false,"fullname":"Jiaan Wang","user":"Krystalan","type":"user"},{"_id":"646def60df618b303b419323","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/646def60df618b303b419323/JLJGYen4-5M8ivsLsSk0w.jpeg","isPro":false,"fullname":"Lei Wang","user":"demolei","type":"user"},{"_id":"699ee1d175b03be202debbd4","avatarUrl":"/avatars/d237fca718bea3c9b1f3ea321eb49d4c.svg","isPro":false,"fullname":"Козлов Никита","user":"benjaminmartin8","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.13120.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2606.13120 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.13120 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2606.13120 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.