{"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/deepresearcher-scaling-deep-research-via","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","arxiv_id":"2504.03160","date":"2025-04-04","proceeding":null,"authors":["Yuxiang Zheng","Dayuan Fu","Xiangkun Hu","Xiaojie Cai","Lyumanshan Ye","Pengrui Lu","PengFei Liu"],"abstract":"Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt engineering-based) with brittle performance or reinforcement learning within controlled Retrieval-Augmented Generation (RAG) environments (RAG-based) that fail to capture the complexities of real-world interaction. In this paper, we introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents through scaling reinforcement learning (RL) in real-world environments with authentic web search interactions. Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web. We implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures and overcoming significant technical challenges. Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines and up to 7.2 points over RAG-based RL agents. Our qualitative analysis reveals emergent cognitive behaviors from end-to-end RL training, including the ability to formulate plans, cross-validate information from multiple sources, engage in self-reflection to redirect research, and maintain honesty when unable to find definitive answers. Our results highlight that end-to-end training in real-world web environments is not merely an implementation detail but a fundamental requirement for developing robust research capabilities aligned with real-world applications. We release DeepResearcher at https://github.com/GAIR-NLP/DeepResearcher.","url_abs":"https://arxiv.org/abs/2504.03160v4","url_pdf":"https://arxiv.org/pdf/2504.03160v4.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":"deepresearcher-scaling-deep-research-via","repo_url":"https://github.com/gair-nlp/deepresearcher","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.03160","atlas_url":"https://app.syntology.ai/?focus=2504.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03160"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gair-nlp/deepresearcher","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/GAIR-NLP/DeepResearcher","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"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":"3d1e7c5cf11a1eb1","entry":"compute_rewards","repo":"GAIR-NLP/DeepResearcher","repo_kind":"official","path":"verl/trainer/ppo/core_algos.py","file_url":"https://github.com/GAIR-NLP/DeepResearcher/blob/HEAD/verl/trainer/ppo/core_algos.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3d1e7c5cf11a1eb1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}