No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from openbmb/AgentCPM-Report
All models by openbmb →
This repository contains AgentCPM-Report, an 8B-parameter deep research agent introduced in the paper AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research.
AgentCPM-Report uses a Writing As Reasoning Policy (WARP) to dynamically revise outlines during report generation, alternating between evidence-based drafting and reasoning-driven deepening to produce high-quality, long-form research reports.
AgentCPM-Report is an open-source large language model agent jointly developed by THUNLP, Renmin University of China RUCBM, and ModelBest. It is based on the MiniCPM4.1 8B-parameter base model. It accepts user instructions as input and autonomously generates long-form reports. Key highlights:
You can watch our demo video here Demo 🔗
You can watch our demo video here Tutorial 🔗
We provide a minimal one-click docker-compose deployment integrated with UltraRAG, including the RAG framework UltraRAG2.0, the model inference framework vllm, and the vector database milvus. If you want CPU inference, we also provide a llama.cpp-based version for gguf models—just switch docker-compose.yml to docker-compose.cpu.yml.
The first startup pulls images, downloads the model, and configures the environment, which takes about 30 minutes.
Then open http://localhost:5050. If you can see the UI, your deployment is successful.
Follow the UI instructions to upload local files, chunk them, and build indexes; then in the Chat section, select AgentCPM-Report in the pipeline to start your workflow.
(Optional) You can import Wiki2024 as the writing database.
You can read more tutorials about AgentCPM-Report in the documentation.
Our evaluation datasets include DeepResearch Bench, DeepConsult, and DeepResearch Gym. The writing-time knowledge base includes about 2.7 million Arxiv papers and about 200,000 internal webpage summaries.
This project would not be possible without the support and contributions of the open-source community. During development, we referred to and used multiple excellent open-source frameworks, models, and data resources, including verl, UltraRAG, MiniCPM4.1, and SurveyGo.
Project leads: Yishan Li, Wentong Chen
Contributors: Yishan Li, Wentong Chen, Yukun Yan, Mingwei Li, Sen Mei, Xiaorong Wang, Kunpeng Liu, Xin Cong, Shuo Wang, Zhong Zhang, Yaxi Lu, Zhenghao Liu, Yankai Lin, Zhiyuan Liu, Maosong Sun
Advisors: Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun
If AgentCPM-Report is helpful for your research, please cite it as follows:
git clone git@github.com:OpenBMB/UltraRAG.gitcd UltraRAGgit checkout agentcpm-report-democd agentcpm-report-democp env.example .envdocker-compose -f docker-compose.yml up -d --builddocker-compose -f docker-compose.yml logs -f ultrarag-ui@misc{li2026agentcpmreport, title={AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research}, author={Yishan Li and Wentong Chen and Yukun Yan and Mingwei Li and Sen Mei and Xiaorong Wang and Kunpeng Liu and Xin Cong and Shuo Wang and Zhong Zhang and Yaxi Lu and Zhenghao Liu and Yankai Lin and Zhiyuan Liu and Maosong Sun}, year={2026}, eprint={2602.06540}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2602.06540}, }