Tongyi DeepResearch Technical Report
By: Tongyi DeepResearch Team , Baixuan Li , Bo Zhang and more
Potential Business Impact:
Helps computers find and understand complex information.
We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous deep research agency, Tongyi DeepResearch is developed through an end-to-end training framework that combines agentic mid-training and agentic post-training, enabling scalable reasoning and information seeking across complex tasks. We design a highly scalable data synthesis pipeline that is fully automatic, without relying on costly human annotation, and empowers all training stages. By constructing customized environments for each stage, our system enables stable and consistent interactions throughout. Tongyi DeepResearch, featuring 30.5 billion total parameters, with only 3.3 billion activated per token, achieves state-of-the-art performance across a range of agentic deep research benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA, xbench-DeepSearch, FRAMES and xbench-DeepSearch-2510. We open-source the model, framework, and complete solutions to empower the community.
Similar Papers
Tongyi DeepResearch Technical Report
Computation and Language
Helps computers find information for deep research.
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
Computation and Language
Helps computers answer hard questions by searching and thinking.
MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework
Computation and Language
Helps doctors find answers to tough medical questions.