DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.
The system adopts a two-layer structure:
- Responsible for understanding, decomposing, and planning the overall workflow for a given task.
- Breaks down tasks into manageable sub-tasks and assigns them to appropriate lower-level agents.
- Dynamically coordinates the collaboration among agents to ensure smooth task completion.
- Deep Analyzer
- Performs in-depth analysis of input information, extracting key insights and potential requirements.
- Supports analysis of various data types, including text and structured data.
- Deep Researcher
- Conducts thorough research on specified topics or questions, retrieving and synthesizing high-quality information.
- Capable of generating research reports or knowledge summaries automatically.
- Browser Use
- Automates browser operations, supporting web search, information extraction, and data collection tasks.
- Assists the Deep Researcher in acquiring up-to-date information from the internet.
- Hierarchical agent collaboration for complex and dynamic task scenarios
- Extensible agent system, allowing easy integration of additional specialized agents
- Automated information analysis, research, and web interaction capabilities
conda create -n dra python=3.11
conda activate dra
make install
.env should be like
PYTHONWARNINGS=ignore # ignore warnings
ANONYMIZED_TELEMETRY=false # disable telemetry
HUGGINEFACE_API_KEY=abcabcabc # your huggingface api key
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_API_KEY=abcabcabc # your openai api key
# (Optional) Local proxy. If you are using a private proxy, please refer to the configuration guide as follows:
LOCAL_PROXY_BASE=http://localhost:6655
SKYWORK_API_BASE=abcabcabs
SKYWORK_OPENROUTER_BJ_API_BASE=abcabcabs
SKYWORK_OPENROUTER_US_API_BASE=abcabcabs
SKYWORK_AZURE_HK_API_BASE=abcabcabs
SKYWORK_WHISPER_BJ_API_BASE=abcabcabs
SKYWORK_GOOGLE_API_BASE=abcabcabs
SKYWORK_API_KEY=abcabcabs
SKYWORK_GOOGLE_SEARCH_API=abcabcabs
python examples/run_example.py
# Download GAIA
mkdir data | cd data
git clone https://huggingface.co/datasets/gaia-benchmark/GAIA
# Run the script in the examples
python examples/run_gaia.py
We evaluated our agent on the GAIA validation set and achieved state-of-the-art performance on May 10th.
DeepResearchAgent is primarily inspired by the architecture of smolagents. The following improvements have been made:
- The codebase of smolagents has been modularized for better structure and organization.
- The original synchronous framework has been refactored into an asynchronous one.
- The multi-agent setup process has been optimized to make it more user-friendly and efficient.
We would like to express our gratitude to the following open source projects, which have greatly contributed to the development of this work:
- smolagents - A lightweight agent framework.
- OpenManus - An asynchronous agent framework.
- browser-use - An AI-powered browser automation tool.
- crawl4ai - A web crawling library for AI applications.
- markitdown - A tool for converting files to Markdown format.
We sincerely appreciate the efforts of all contributors and maintainers of these projects for their commitment to advancing AI technologies and making them available to the wider community.
Contributions and suggestions are welcome! Feel free to open issues or submit pull requests to improve the project.
@misc{DeepResearchAgent,
title = {`DeepResearchAgent`: A Hierarchical Multi-Agent Framework for General-purpose Task Solving.},
author = {Wentao Zhang, Ce Cui, Yang Liu, Bo An},
howpublished = {\url{https://github.com/SkyworkAI/DeepResearchAgent}},
year = {2025}
}