metadata
pipeline_tag: text-generation
library_name: transformers
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
This model, DeepResearcher-7b, is presented in the paper DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments.
DeepResearcher is 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. Qualitative analysis reveals emergent cognitive behaviors from end-to-end RL training, including the ability to formulate plans, cross-validate information, engage in self-reflection, and maintain honesty when unable to find definitive answers. Experiments on open-domain research tasks demonstrate substantial improvements over prompt engineering and RAG-based RL agents.