{"id":45189829,"url":"https://github.com/TIGER-AI-Lab/OpenResearcher","last_synced_at":"2026-03-05T09:01:16.629Z","repository":{"id":337525121,"uuid":"1148429262","full_name":"TIGER-AI-Lab/OpenResearcher","owner":"TIGER-AI-Lab","description":"OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis","archived":false,"fork":false,"pushed_at":"2026-02-24T01:20:42.000Z","size":8348,"stargazers_count":386,"open_issues_count":0,"forks_count":41,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-24T03:01:58.212Z","etag":null,"topics":["deep-research","llm","retrieval"],"latest_commit_sha":null,"homepage":"https://github.com/TIGER-AI-Lab/OpenResearcher","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TIGER-AI-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-03T00:34:05.000Z","updated_at":"2026-02-24T02:28:57.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/TIGER-AI-Lab/OpenResearcher","commit_stats":null,"previous_names":["tiger-ai-lab/openresearcher"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TIGER-AI-Lab/OpenResearcher","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FOpenResearcher","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FOpenResearcher/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FOpenResearcher/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FOpenResearcher/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TIGER-AI-Lab","download_url":"https://codeload.github.com/TIGER-AI-Lab/OpenResearcher/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FOpenResearcher/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30117470,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T08:19:04.902Z","status":"ssl_error","status_checked_at":"2026-03-05T08:17:37.148Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-research","llm","retrieval"],"created_at":"2026-02-20T12:00:23.661Z","updated_at":"2026-03-05T09:01:16.617Z","avatar_url":"https://github.com/TIGER-AI-Lab.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./assets/imgs/or-logo1.png\" height=\"82\" style=\"vertical-align: middle;\"\u003e\n  \u003cimg src=\"./assets/imgs/openresearcher-title.svg\" height=\"66\" style=\"vertical-align: middle;\"\u003e\u003c/p\u003e\n\n\u003cdiv align=\"center\" style=\"line-height: 1; margin-top: 16px;\"\u003e\n\n\u003cdiv align=\"center\"\u003e\n    \u003ca href=\"https://x.com/DongfuJiang/status/2020946549422031040\"\u003e\u003cimg src=\"https://img.shields.io/badge/Twitter-000000?style=for-the-badge\u0026logo=X\u0026logoColor=white\" alt=\"Blog\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://boiled-honeycup-4c7.notion.site/OpenResearcher-A-Fully-Open-Pipeline-for-Long-Horizon-Deep-Research-Trajectory-Synthesis-2f7e290627b5800cb3a0cd7e8d6ec0ea?source=copy_link\"\u003e\u003cimg src=\"https://img.shields.io/badge/Blog-4285F4?style=for-the-badge\u0026logo=google-chrome\u0026logoColor=white\" alt=\"Blog\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/TIGER-AI-Lab/OpenResearcher\"\u003e\u003cimg src=\"https://img.shields.io/badge/Github-181717?style=for-the-badge\u0026logo=github\u0026logoColor=white\" alt=\"Blog\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset\"\u003e\u003cimg src=\"https://img.shields.io/badge/Dataset-FFB7B2?style=for-the-badge\u0026logo=huggingface\u0026logoColor=ffffff\" alt=\"Dataset\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/OpenResearcher/OpenResearcher-30B-A3B\"\u003e\u003cimg src=\"https://img.shields.io/badge/Model-FFD966?style=for-the-badge\u0026logo=huggingface\u0026logoColor=ffffff\" alt=\"Model\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://huggingface.co/spaces/OpenResearcher/OpenResearcher\"\u003e\u003cimg src=\"https://img.shields.io/badge/Demo-F97316.svg?style=for-the-badge\u0026logo=gradio\u0026logoColor=white\" alt=\"Demo\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://x.com/zhuofengli96475/status/2021682952074097086\"\u003e\u003cimg src=\"https://img.shields.io/badge/Video-CA4245?style=for-the-badge\u0026logo=youtube\u0026logoColor=white\" alt=\"Video\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Eval-Logs/tree/main\"\u003e\u003cimg src=\"https://img.shields.io/badge/Eval%20Logs-755BB4?style=for-the-badge\u0026logo=google-sheets\u0026logoColor=white\" alt=\"Eval Logs\"\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n\u003c/div\u003e\n\u003cbr\u003e\n\u003cp align=\"center\"\u003e\n  🤗 \u003ca href=\"https://huggingface.co/collections/TIGER-Lab/openresearcher\" target=\"_blank\"\u003eHuggingFace\u003c/a\u003e ｜\n\u003cimg src=\"assets/imgs/notion.svg\" width=\"15px\" style=\"display:inline;\"\u003e \u003ca href=\"https://boiled-honeycup-4c7.notion.site/OpenResearcher-A-Fully-Open-Pipeline-for-Long-Horizon-Deep-Research-Trajectory-Synthesis-2f7e290627b5800cb3a0cd7e8d6ec0ea?source=copy_link\" target=\"_blank\"\u003eBlog\u003c/a\u003e ｜\u003cimg src=\"assets/imgs/slack.png\" width=\"14px\" style=\"display:inline;\"\u003e \u003ca href=\"https://join.slack.com/t/openresearcher/shared_invite/zt-3p0r32cky-PqtZkVjjWIAI14~XwcRMfQ\" target=\"_blank\"\u003eSlack\u003c/a\u003e | \u003cimg src=\"assets/imgs/wechat.svg\" width=\"14px\" style=\"display:inline;\"\u003e \u003ca href=\"assets/imgs/wechat_group.jpg\" target=\"_blank\"\u003eWeChat\u003c/a\u003e \n\u003c/p\u003e\n\n## 📣 News \n+ **[2026.2.25]** 🔥 Honored to be among the **top 3 trending datasets** on 🤗 [Hugging Face](https://huggingface.co/datasets) — now **11K+** downloads! 🚀\n+ **[2026.2.18]** 🧪 The OpenResearcher training [code](https://github.com/TIGER-AI-Lab/OpenResearcher?tab=readme-ov-file#-optional-train-your-own-openresearcher) is now available. Start training your own OpenResearcher!\n+ **[2026.2.14]** 📸 Excited to have our OpenResearcher demo [video](https://x.com/zhuofengli96475/status/2021682952074097086). Dive in and unlock the power of Deep Research today!\n+ **[2026.2.12]**  🔥 Excited to see **OpenResearcher** powering deep research trajectory generation in [**NVIDIA’s NeMo Data Designer**](https://nvidia-nemo.github.io/DataDesigner/latest/devnotes/deep-research-trajectories-with-nemo-data-designer-and-mcp-tool-use/)!\n+ **[2026.2.10]** 🚀 Our X [post](https://x.com/DongfuJiang/status/2020946549422031040) received **1.2K+ likes**! Feel free to check out the post and join the discussion! 💬\n\n## 💥 Introduction\n\n**OpenResearcher** is a fully open agentic large language model (30B-A3B) designed for **long-horizon deep research** scenarios. It achieves an impressive **54.8%** accuracy on [BrowseComp-Plus](https://huggingface.co/spaces/Tevatron/BrowseComp-Plus), surpassing performance of `GPT-4.1`, `Claude-Opus-4`, `Gemini-2.5-Pro`, `DeepSeek-R1` and `Tongyi-DeepResearch`. We **fully open-source** the training and evaluation recipe—including data, model, training methodology, and evaluation framework for everyone to progress deep research.\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/imgs/teaser.png\" alt=\"OpenResearcher Teaser\" width=\"100%\" style=\"max-width: 850px; border-radius: 8px; box-shadow: 0 4px 10px rgba(0,0,0,0.1);\"\u003e\n\u003c/div\u003e\n\n\u003cbr\u003e\n\n## 🏆 Deep Research Benchmark Results\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/imgs/main_table.png\" alt=\"Deep Research Benchmark Results\" width=\"100%\"\u003e\n\u003c/div\u003e\n\n\n## ✨ Features\n+ 🔑 **Fully Open-Source Recipe** — We fully open-source our 96K high-quality [DeepResearch trajectory dataset](https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset) with 100+ turns generated by GPT-OSS-120B with [native browser tools](https://docs.vllm.ai/projects/recipes/en/latest/OpenAI/GPT-OSS.html#usage:~:text=Limitation%20section%20below.-,Tool%20Use,-%C2%B6), the leading [30B-A3B model](https://huggingface.co/OpenResearcher/OpenResearcher-30B-A3B) trained on it, [distillation recipe](https://boiled-honeycup-4c7.notion.site/OpenResearcher-A-Fully-Open-Pipeline-for-Long-Horizon-Deep-Research-Trajectory-Synthesis-2f7e290627b5800cb3a0cd7e8d6ec0ea?source=copy_link), and a lightweight [DeepResearch evaluation framework](https://github.com/TIGER-AI-Lab/OpenResearcher) to progress deep research.\n\n+ 💰 **Highly Scalable and Low-Cost** — We generate DeepResearch trajectories at massive scale using self-built retriever over a dedicated ~11B-token [corpus](https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Corpus), eliminating the need for external Search APIs. This scalable retriever significantly reduces training costs.\n\n+ 🚀 **Remarkable Performance on Deep Research Benchmarks** — OpenResearcher demonstrates leading performance across a range of deep research benchmarks, including BrowseComp-Plus, BrowseComp, GAIA, xbench-DeepSearch.\n\n## 📋 Table of Contents\n\n- [🛠 Environment Setup](#-environment-setup)\n  - [Installation](#installation)\n  - [Deep Research Benchmarks Preparation](#deep-research-benchmarks-preparation)\n- [🔍 Configuration](#-configuration)\n- [🚀 Quick Start](#-quick-start)\n- [🔬 Benchmark OpenResearcher](#-benchmark-openresearcher)\n  - [Example 1: BrowseComp-Plus with Local Search Engine](#example-1-browsecomp-plus-with-local-search-engine)\n  - [Example 2: GAIA with Serper API (No Local Search Needed)](#example-2-gaia-with-serper-api-no-local-search-needed)\n  - [Evaluation](#evaluation)\n  - [Quick Commands](#quick-commands)\n- [🧪 (Optional) Train Your Own OpenResearcher](#-optional-train-your-own-openresearcher)\n- [🤝 Core Contributors](#-core-contributors)\n- [🎓 Advisors](#-advisors)\n- [🙏 Acknowledgements](#-acknowledgements)\n- [✨ Contributing](#-contributing)\n- [📚 Citation](#-citation)\n## 🛠 Environment Setup\nWe run this repo on the following setup:\n+ 8 * A100 80G Nvidia GPUs\n+ Linux operating system\n\nOther hardware setups can also work, but remember to modify the corresponding parameters.\n### Installation \n```bash\nsudo apt update \nsudo apt install -y openjdk-21-jdk\n\n# install uv\ncurl -LsSf https://astral.sh/uv/install.sh | sh\nuv venv --python 3.12\nsource .venv/bin/activate\n\n# install tevatron for BrowseComp-plus \ngit clone https://github.com/texttron/tevatron.git\ncd tevatron\nuv pip install -e .\ncd ..\n\n# install all dependencies automatically\nuv pip install -e .\n```\n\n### Deep Research Benchmarks Preparation\n\nRun the setup script to automatically download the **[BrowseComp-Plus](https://arxiv.org/abs/2508.06600)** benchmark. Other benchmarks, including **[BrowseComp](https://arxiv.org/abs/2504.12516)**, **[GAIA](https://arxiv.org/abs/2311.12983)** and **[xbench-DeepResearch](https://github.com/THUDM/xbench)**, will be set up automatically when they are first used.\n\n```bash\nbash setup.sh\n```\n\n**This script will:**\n- ✅ Verify Python 3.12 virtual environment and automatically install any missing dependencies\n- ✅ Downlaod BrowseComp-Plus dataset from HuggingFace and set up the directory structure\n\nFor more info about these deep research benchmarks, see [benchmarks.md](assets/docs/benchmarks.md) \n\n## 🔍 Configuration\n\nCopy the template and configure your API keys:\n\n```bash\ncp .env.template .env\n```\n\nEdit `.env`:\n```bash\n# Serper API (for web search when using browser_backend=serper)\nSERPER_API_KEY=your_key        # Get from: https://serper.dev/\n\n# OpenAI API (for evaluation scoring)\nOPENAI_API_KEY=your_key        # Get from: https://platform.openai.com/api-keys\n```\n\n\n## 🚀 Quick Start\n**Prerequisites:** Install dependencies and configure API keys (see [Environment Setup](#-environment-setup) and [Configuration](#-configuration))\n\n1. **Deploy OpenResearcher-30B-A3B**:\n\n```bash\nbash scripts/start_nemotron_servers.sh\n```\n\nThe complete vLLM server logs can be found in the `logs` directory.\n\n2. **Run your first task** (Before proceeding, check the logs in `logs` directory to ensure the vLLM server is deployed.)\n\n```python\nimport asyncio\nfrom deploy_agent import run_one, BrowserPool\nfrom utils.openai_generator import OpenAIAsyncGenerator\n\nasync def main():\n    # Initialize generator and browser\n    generator = OpenAIAsyncGenerator(\n        base_url=\"http://localhost:8001/v1\",\n        model_name=\"OpenResearcher/OpenResearcher-30B-A3B\",\n        use_native_tools=True\n    )\n    browser_pool = BrowserPool(search_url=None, browser_backend=\"serper\")\n\n    # Run deep research\n    await run_one(\n        question=\"What is the latest news about OpenAI?\",\n        qid=\"quick_start\",\n        generator=generator,\n        browser_pool=browser_pool,\n    )\n\n    browser_pool.cleanup(\"quick_start\")\n\nif __name__ == \"__main__\":\n    asyncio.run(main())\n```\n\nThe deep research agent will automatically search the web, browse webpages, and extract relevant information. You'll see the final answer along with all intermediate reasoning steps.\n\n\n## 🔬 Benchmark OpenResearcher\nWe benchmark our OpenResearcher-30B-A3B using below deep research benchmarks: \n\n| Benchmark | Dataset Key | Size | Language | Search Backend | Description |\n|-----------|-------------|------|----------|----------------|-------------|\n| [BrowseComp-Plus](https://arxiv.org/abs/2508.06600) | `browsecomp_plus` | 830 | EN | local | Deep-research benchmark from BrowseComp isolating retriever and LLM agent effects |\n| [BrowseComp](https://arxiv.org/abs/2504.12516) | `browsecomp` | 1,266 | EN | serper | A Simple Yet Challenging Benchmark for Browsing Agents |\n| [GAIA-text](https://arxiv.org/abs/2311.12983) | `gaia` | 103 | EN | serper | Text-only subset of GAIA benchmark (dev split) |\n| [xbench-DeepResearch](https://github.com/THUDM/xbench) | `xbench` | 100 | ZH | serper | DeepSearch benchmark with encrypted test cases |\n\nFor more info about these deep research benchmarks, see [benchmarks.md](assets/docs/benchmarks.md) \n\n### Example 1: BrowseComp-Plus with Local Search Engine\n\nComplete evaluation using local dense search with browsecomp-plus [corpus](https://huggingface.co/datasets/Tevatron/browsecomp-plus-corpus) and [embeddings](https://huggingface.co/datasets/Tevatron/browsecomp-plus-indexes/tree/main/qwen3-embedding-8b) (**note: only applicable for BrowseComp-Plus**):\n\n```bash\n# Terminal 1: Start local Dense search service on port 8000\n# Embedding model (Qwen3-Embedding-8B) will be deployed on GPUs 7\nbash scripts/start_search_service.sh dense 8000\n\n# Terminal 2: Start vLLM servers (requires 4 GPUs)\n# TP=2, deploy 2 servers starting from port 8001 on GPUs 0,1,2,3\nbash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3\n\n# Terminal 3: Run agent\nbash run_agent.sh results/browsecomp_plus/OpenResearcher_dense 8001 2 browsecomp_plus local OpenResearcher/OpenResearcher-30B-A3B\n```\n\nWhat this does:\n- Deploys Dense retriever service on port 8000 as search engine\n- Launches 2 vLLM servers (ports 8001, 8002) with TP=2 across 4 GPUs\n- Runs deepresearch agent with load balancing across both servers\n\n### Example 2: GAIA with Serper API (No Local Search Needed)\n\nRun with Serper Google Search API (**note: applicable to all benchmarks except BrowseComp-Plus**):\n\n```bash\n# Terminal 1: Start vLLM servers (requires 4 GPUs)\nbash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3\n\n# Terminal 2: Run agent with serper search backend\nbash run_agent.sh results/gaia/OpenResearcher_serper 8001 2 gaia serper OpenResearcher/OpenResearcher-30B-A3B\n```\n\n**Browser Backend Options:**\n- `local` - Use local BM25/Dense search service (for BrowseComp-Plus)\n- `serper` - Use Serper Google Search API (for all other benchmarks)\n\nFor other parameters, refer to [parameter.md](assets/docs/parameter.md).\n\n### Evaluation\n\nAfter running experiments, evaluate results:\n\n```bash\n# eval on browsecomp_plus\npython eval.py --input_dir results/browsecomp_plus_dense/OpenResearcher_dense\n\n# eval on gaia\npython eval.py --input_dir results/gaia/OpenResearcher_serper\n```\n\n### Quick Commands\n\n| Scenario | Command |\n|----------|---------|\n| BrowseComp-Plus (BM25) | `bash scripts/start_search_service.sh bm25 8000` then `bash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3` then `bash run_agent.sh results/browsecomp-plus/OpenResearcher_bm25 8001 2 browsecomp_plus local OpenResearcher/OpenResearcher-30B-A3B` |\n| BrowseComp-Plus (Qwen3-8B Dense Embeddings) | `bash scripts/start_search_service.sh dense 8000` then `bash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3` then `bash run_agent.sh results/browsecomp-plus/OpenResearcher_dense 8001 2 browsecomp-plus local OpenResearcher/OpenResearcher-30B-A3B` |\n| BrowseComp | `bash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3` then `bash run_agent.sh results/browsecomp 8001 2 browsecomp serper OpenResearcher/OpenResearcher-30B-A3B` |\n| GAIA | `bash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3` then `bash run_agent.sh results/gaia 8001 2 gaia serper OpenResearcher/OpenResearcher-30B-A3B` |\n| xbench-DeepResearch | `bash scripts/start_nemotron_servers.sh 2 8001 0,1,2,3` then `bash run_agent.sh results/xbench 8001 2 xbench serper OpenResearcher/OpenResearcher-30B-A3B` |\n\nFor script parameter explanation, refer to [parameter.md](assets/docs/parameter.md).\n\n**Note:** Don't forget to evaluate your results using:  \n```bash\npython eval.py --input_dir [INPUT_DIR]\n```\n\n## 🧪 (Optional) Train Your Own OpenResearcher\n\nOur [OpenResearcher-30B-A3B](https://huggingface.co/OpenResearcher/OpenResearcher-30B-A3B) is trained using [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) on [openresearcher-dataset](https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset). To get started, clone the `openresearcher` branch of the Megatron-LM repository:\n```\ngit clone -b openresearcher https://github.com/jdf-prog/Megatron-LM.git\n```\nThen, follow the training instructions [here](https://github.com/jdf-prog/Megatron-LM/tree/openresearcher/examples/openresearcher) to train your own OpenResearcher!\n\n## 🤝 Core Contributors\n\n\u003ctable\u003e\n\u003ctr\u003e\n    \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://zhuofeng-li.github.io/\"\u003e\n            \u003cimg src=\"https://github.com/Zhuofeng-Li.png\" width=\"75px;\" alt=\"Zhuofeng Li\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eZhuofeng Li\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n        \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://github.com/jdf-prog\"\u003e\n            \u003cimg src=\"https://github.com/jdf-prog.png\" width=\"75px;\" alt=\"Dongfu Jiang\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eDongfu Jiang\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n    \u003c/td\u003e\n        \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://mxueguang.github.io/\"\u003e\n            \u003cimg src=\"https://mxueguang.github.io/images/profile.jpg\" width=\"75px;\" alt=\"Xueguang\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eXueguang Ma\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://isaacghx.github.io/about/\"\u003e\n            \u003cimg src=\"https://github.com/IsaacGHX.png\" width=\"75px;\" alt=\"Haoxiang Zhang\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eHaoxiang Zhang\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://github.com/erenup\"\u003e\n            \u003cimg src=\"https://github.com/erenup.png\" width=\"75px;\" alt=\"Ping Nie\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003ePing Nie\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## 🎓 Advisors\n\n\u003ctable\u003e\n\u003ctr\u003e\n      \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://github.com/wenhuchen\"\u003e\n            \u003cimg src=\"https://github.com/wenhuchen.png\" width=\"75px;\" alt=\"Wenhu Chen\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eWenhu Chen\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\n        \u003ca href=\"https://yuzhimanhua.github.io/\"\u003e\n            \u003cimg src=\"https://yuzhimanhua.github.io/profile_pic.jpg\" width=\"75px;\" alt=\"Yu Zhang\"/\u003e\n            \u003cbr /\u003e\n            \u003csub\u003e\u003cb\u003eYu Zhang\u003c/b\u003e\u003c/sub\u003e\n        \u003c/a\u003e\n    \u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n## 🙏 Acknowledgements\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/imgs/ack.png\" alt=\"Deep Research Benchmark Results\" width=\"100%\"\u003e\n\u003c/div\u003e\n\n\n## ✨ Contributing\nWe are truly looking forward to open-source contributions to OpenResearcher! If you’re interested in contributing, collaborating, or reporting issues, please feel free to open an issue or submit a pull request (PR). You can also reach us at [zhuofengli12345@gmail.com](mailto:zhuofengli12345@gmail.com).\n\nWe are also looking forward to your feedback and suggestions!\n\n##  📚 Citation\n\n```bibtex\n@misc{li2025openresearcher,\n  title={OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis},\n  author={Zhuofeng Li and Dongfu Jiang and Xueguang Ma and Haoxiang Zhang and Ping Nie and Yuyu Zhang and Kai Zou and Jianwen Xie and Yu Zhang and Wenhu Chen},\n  year={2025},\n  howpublished={\\url{https://www.notion.so/OpenResearcher-A-Fully-Open-Pipeline-for-Long-Horizon-Deep-Research-Trajectory-Synthesis-2f7e290627b5800cb3a0cd7e8d6ec0ea}},\n  note={Notion Blog}\n}\n```\n\n## ⭐ Star History\n[![Star History Chart](https://api.star-history.com/svg?repos=TIGER-AI-Lab/OpenResearcher\u0026type=date\u0026legend=top-left)](https://www.star-history.com/#TIGER-AI-Lab/OpenResearcher\u0026type=date\u0026legend=top-left)\n\n\u003cp align=\"right\" style=\"font-size: 14px; margin-top: 20px;\"\u003e\n  \u003ca href=\"#readme-top\" style=\"text-decoration: none; font-weight: bold;\"\u003e\n    ↑ Back to Top ↑\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTIGER-AI-Lab%2FOpenResearcher","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTIGER-AI-Lab%2FOpenResearcher","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTIGER-AI-Lab%2FOpenResearcher/lists"}