---
title: "DeepResearch"
type: "tool"
slug: "alibaba-nlp-deepresearch"
canonical_url: "https://www.graphcanon.com/tools/alibaba-nlp-deepresearch"
github_url: "https://github.com/Alibaba-NLP/DeepResearch"
homepage_url: "https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/"
stars: 19617
forks: 1499
primary_language: "Python"
license: "Apache-2.0"
categories: ["ai-agents", "llm-frameworks"]
tags: ["llm", "artificial-intelligence", "tongyi", "alibaba", "deep-research", "agent"]
updated_at: "2026-07-07T18:27:06.880778+00:00"
---

# DeepResearch

> Tongyi Deep Research: Leading Open-source Deep Research Agent

An agent-based large language model specialized for long-horizon and deep information-seeking tasks. Developed by Alibaba's Tongyi Lab, it excels in various agentic search benchmarks.

## Facts

- Repository: https://github.com/Alibaba-NLP/DeepResearch
- Homepage: https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/
- Stars: 19,617 · Forks: 1,499 · Open issues: 91 · Watchers: 126
- Primary language: Python
- License: Apache-2.0
- Last pushed: 2026-02-27T13:12:11+00:00

## Categories

- [AI Agents](/categories/ai-agents.md)
- [LLM Frameworks](/categories/llm-frameworks.md)

## Tags

llm, artificial-intelligence, tongyi, alibaba, deep-research, agent

## Related tools

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (★ 226,962)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (★ 210,880)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (★ 185,417)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (★ 148,070)

## README (excerpt)

```text
<div align="center">
  <picture>
      <img src="./assets/logo.png" width="100%">
  </picture>
</div>

<hr>

<div align="center" style="line-height: 1;">






</div>
<p align="center">
<p align="center">
🤗 <a href="https://huggingface.co/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B" target="_blank">HuggingFace</a> ｜
<img src="./assets/tongyi.png" width="14px" style="display:inline;"> <a href="https://modelscope.cn/models/iic/Tongyi-DeepResearch-30B-A3B" target="_blank">ModelScope</a> | 💬 <a href="./assets/wechat_new.jpg">WeChat(微信)</a> | 📰 <a href="https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/">Blog</a> | 📑 <a href="https://arxiv.org/pdf/2510.24701">Paper</a>

<p align="center">
<a href="https://trendshift.io/repositories/14895" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14895" alt="Alibaba-NLP%2FDeepResearch | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

👏 Welcome to try Tongyi DeepResearch via our **[<img src="./assets/tongyi.png" width="14px" style="display:inline;"> Modelscope online demo](https://www.modelscope.cn/studios/jialongwu/Tongyi-DeepResearch)** or **[🤗 Huggingface online demo](https://huggingface.co/spaces/Alibaba-NLP/Tongyi-DeepResearch)** or <img src="./WebAgent/assets/aliyun.png" width="14px" style="display:inline;"> **[bailian service](https://bailian.console.aliyun.com/?spm=a2ty02.31808181.d_app-market.1.6c4974a1tFmoFc&tab=app#/app/app-market/deep-search/)**!

> [!NOTE]
> This demo is for quick exploration only. Response times may vary or fail intermittently due to model latency and tool QPS limits. For a stable experience we recommend local deployment; for a production-ready service, visit <img src="./WebAgent/assets/aliyun.png" width="14px" style="display:inline;"> [bailian](https://bailian.console.aliyun.com/?spm=a2ty02.31808181.d_app-market.1.6c4974a1tFmoFc&tab=app#/app/app-market/deep-search/) and follow the guided setup.

# Introduction

We present <img src="./assets/tongyi.png" width="14px" style="display:inline;"> **Tongyi DeepResearch**, an agentic large language model featuring 30.5 billion total parameters, with only 3.3 billion activated per token. Developed by Tongyi Lab, the model is specifically designed for **long-horizon, deep information-seeking** tasks. Tongyi DeepResearch demonstrates state-of-the-art performance across a range of agentic search benchmarks, including Humanity's Last Exam, BrowseComp, BrowseComp-ZH, WebWalkerQA,xbench-DeepSearch, FRAMES and SimpleQA.

> Tongyi DeepResearch builds upon our previous work on the <img src="./assets/tongyi.png" width="14px" style="display:inline;"> [WebAgent](./WebAgent/) project.

More details can be found in our 📰&nbsp;<a href="https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/">Tech Blog</a>.

<p align="center">
  <img width="100%" src="./assets/performance.png">
</p>

## Features

- ⚙️ **Fully automated synthetic data generation pipeline**: We design a highly scalable data synthesis pipeline, which is fully automatic and empowers agentic pre-training, supervised fine-tuning, and reinforcement learning.
- 🔄 **Large-scale continual pre-training on agentic data**: Leveraging diverse, high-quality agentic interaction data to extend model capabilities, maintain freshness, and strengthen reasoning performance.
- 🔁 **End-to-end reinforcement learning**: We employ a strictly on-policy RL approach based on a customized Group Relative Policy Optimization framework, with token-level policy gradients, leave-one-out advantage estimation, and selective filtering of negative samples to stabilize training in a non‑stationary environment.
- 🤖 **Agent Inference Paradigm Compatibility**: At inference, Tongyi DeepResearch is compatible with two inference paradigms: ReAct, for rigorously evaluating the model's core intrinsic abilities, and an IterResearch-based 'Heavy' mode, which uses a test-time scaling strategy to unlock the model's maximum perform
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/alibaba-nlp-deepresearch`](/api/graphcanon/tools/alibaba-nlp-deepresearch)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_