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.
git clone git@github.com:OpenBMB/UltraRAG.git
cd UltraRAG
git checkout agentcpm-report-demo
cd agentcpm-report-demo
cp env.example .env
docker-compose -f docker-compose.yml up -d --build
docker-compose -f docker-compose.yml logs -f ultrarag-ui
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.
If AgentCPM-Report is helpful for your research, please cite it as follows:
@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},
}
Files
17 files · 16.4 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("openbmb/AgentCPM-Report", revision="c6232d64a47ccfa0c4aed240d325cbc0fb9cbc62")
model = AutoModelForCausalLM.from_pretrained("openbmb/AgentCPM-Report", revision="c6232d64a47ccfa0c4aed240d325cbc0fb9cbc62", device_map="auto")
