{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/webthinker-empowering-large-reasoning-models","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","arxiv_id":"2504.21776","date":"2025-04-30","proceeding":null,"authors":["Xiaoxi Li","Jiajie Jin","Guanting Dong","Hongjin Qian","Yutao Zhu","Yongkang Wu","Ji-Rong Wen","Zhicheng Dou"],"abstract":"Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose \\textbf{WebThinker}, a deep research agent that empowers LRMs to autonomously search the web, navigate web pages, and draft research reports during the reasoning process. WebThinker integrates a \\textbf{Deep Web Explorer} module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an \\textbf{Autonomous Think-Search-and-Draft strategy}, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an \\textbf{RL-based training strategy} via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems. The code is available at https://github.com/RUC-NLPIR/WebThinker.","url_abs":"https://arxiv.org/abs/2504.21776v1","url_pdf":"https://arxiv.org/pdf/2504.21776v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"webthinker-empowering-large-reasoning-models","repo_url":"https://github.com/ruc-nlpir/webthinker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"webthinker-empowering-large-reasoning-models","repo_url":"https://github.com/sunnynexus/webthinker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"webthinker-empowering-large-reasoning-models","repo_url":"https://github.com/sunnynexus/search-o1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.21776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21776"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/RUC-NLPIR/WebThinker","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunnynexus/search-o1","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunnynexus/webthinker","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ruc-nlpir/webthinker","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"78ada9e8a4f42590","entry":"extract_answer_fn","repo":"RUC-NLPIR/WebThinker","repo_kind":"official","path":"scripts/evaluate/evaluate.py","file_url":"https://github.com/RUC-NLPIR/WebThinker/blob/HEAD/scripts/evaluate/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78ada9e8a4f42590"}},{"code_sha256_prefix":"626c668b26597459","entry":"extract_between","repo":"RUC-NLPIR/WebThinker","repo_kind":"official","path":"scripts/run_web_thinker.py","file_url":"https://github.com/RUC-NLPIR/WebThinker/blob/HEAD/scripts/run_web_thinker.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"626c668b26597459"}},{"code_sha256_prefix":"612fdb95a37c630c","entry":"format_search_results","repo":"RUC-NLPIR/WebThinker","repo_kind":"official","path":"scripts/run_web_thinker.py","file_url":"https://github.com/RUC-NLPIR/WebThinker/blob/HEAD/scripts/run_web_thinker.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"612fdb95a37c630c"}},{"code_sha256_prefix":"da6719339b1894c5","entry":"get_multiqa_search_o1_instruction","repo":"sunnynexus/webthinker","repo_kind":"official","path":"demo/prompts.py","file_url":"https://github.com/sunnynexus/webthinker/blob/HEAD/demo/prompts.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da6719339b1894c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}