DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments

Pengfei Liu, Xiangkun Hu, Dayuan Fu, Lyumanshan Ye, Yuxiang Zheng, Xiaojie Cai, Pengrui Lu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• gair-nlp/deepresearcher — marked official in Papers with Code; named in the paper
• GAIR-NLP/DeepResearcher

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) with web search capabilities show significant potential for deep research, yet current methods-brittle prompt engineering or RAG-based reinforcement learning in controlled environments-fail to capture real-world complexities. 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 approaches reliant on fixed corpora, DeepResearcher trains agents to navigate the noisy, dynamic 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, such as planning, cross-validation, self-reflection for research redirection, and maintain honesty when unable to find definitive answers. Our results highlight that end-to-end training in realworld web environments is fundamental for developing robust research capabilities aligned with real-world applications. The source code for DeepResearcher is released at: https:// github.com/GAIR-NLP/DeepResearcher.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2504.03160")
get_code_for_paper("2504.03160")
have("2504.03160")

Connect an agent — have() is free.