Total runs:
173.2K
Run Growth:
55.7K
Growth Rate:
33.72%
Sponsored by
APIMart
openbmb / AgentCPM-Report
Model's Last Updated: February 11 2026
text-generation
Introduction of AgentCPM-Report
Model Details of AgentCPM-Report
AgentCPM-Report: Gemini-2.5-pro-DeepResearch Level Local DeepResearch
Links & Resources
📊 AgentCPM-Report Models
- AgentCPM-Report The Gemini-2.5-pro-DeepResearch Level Local DeepResearch Model
- AgentCPM-Report-GGUF The GGUF version of AgentCPM-Report
🤖 AgentCPM-Explore Models
- AgentCPM-Explore The first open-source agent model with 4B parameters to appear on 8 widely used long-horizon agent benchmarks.
- AgentCPM-Explore-GGUF The GGUF version of AgentCPM-Explore
💻 Code & Framework
- AgentCPM Our code for AgentCPM Series
- UltraRAG A RAG Framework, Less Code, Lower Barrier, Faster Deployment
News
- [2026-01-20] 🚀🚀🚀 We open-sourced AgentCPM-Report built on MiniCPM4.1-8B, capable of matching top closed-source commercial systems like Gemini-2.5-pro-DeepResearch in report generation.
Overview
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:
- Extreme Performance, Minimal Footprint : Through an average of 40 rounds of deep retrieval and nearly 100 rounds of chain-of-thought reasoning, it achieves comprehensive information mining and restructuring, enabling edge-side models to produce logically rigorous, deeply insightful long-form articles with tens of thousands of words. With just 8 billion parameters, it delivers performance on par with top-tier closed-source systems in deep research tasks.
- Physical Isolation, Local Security : Specifically designed for high-privacy scenarios, it supports fully offline and agile local deployment, completely eliminating the risk of cloud data leaks. Leveraging our UltraRAG framework, it efficiently mounts and understands your local private knowledge base, securely transforming core confidential data into highly valuable professional decision-making reports without ever leaving its domain.
Demo Cases
You can watch our demo video here Demo 🔗
Quick Start
Docker Deployment
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
.
git clone [email protected]: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 .
Evaluation
| DeepResearch Bench | Overall | Comprehensiveness | Insight | Instruction Following | Readability |
|---|---|---|---|---|---|
| Doubao-research | 44.34 | 44.84 | 40.56 | 47.95 | 44.69 |
| Claude-research | 45.00 | 45.34 | 42.79 | 47.58 | 44.66 |
| OpenAI-deepresearch | 46.45 | 46.46 | 43.73 | 49.39 | 47.22 |
| Gemini-2.5-Pro-deepresearch | 49.71 | 49.51 | 49.45 | 50.12 | 50.00 |
| WebWeaver(Qwen3-30B-A3B) | 46.77 | 45.15 | 45.78 | 49.21 | 47.34 |
| WebWeaver(Claude-Sonnet-4) | 50.58 | 51.45 | 50.02 | 50.81 | 49.79 |
| Enterprise-DR(Gemini-2.5-Pro) | 49.86 | 49.01 | 50.28 | 50.03 | 49.98 |
| RhinoInsigh(Gemini-2.5-Pro) | 50.92 | 50.51 | 51.45 | 51.72 | 50.00 |
| AgentCPM-Report | 50.11 | 50.54 | 52.64 | 48.87 | 44.17 |
| DeepResearch Gym | Avg. | Clarity | Depth | Balance | Breadth | Support | Insightfulness |
|---|---|---|---|---|---|---|---|
| Doubao-research | 84.46 | 68.85 | 93.12 | 83.96 | 93.33 | 84.38 | 83.12 |
| Claude-research | 80.25 | 86.67 | 96.88 | 84.41 | 96.56 | 26.77 | 90.22 |
| OpenAI-deepresearch | 91.27 | 84.90 | 98.10 | 89.80 | 97.40 | 88.40 | 89.00 |
| Gemini-2.5-pro-deepresearch | 96.02 | 90.71 | 99.90 | 93.37 | 99.69 | 95.00 | 97.45 |
| WebWeaver (Qwen3-30b-a3b) | 77.27 | 71.88 | 85.51 | 75.80 | 84.78 | 63.77 | 81.88 |
| WebWeaver (Claude-sonnet-4) | 96.77 | 90.50 | 99.87 | 94.30 | 100.00 | 98.73 | 97.22 |
| AgentCPM-Report | 98.48 | 95.10 | 100.00 | 98.50 | 100.00 | 97.30 | 100.00 |
| DeepConsult | Avg. | Win | Tie | Lose |
|---|---|---|---|---|
| Doubao-research | 5.42 | 29.95 | 40.35 | 29.70 |
| Claude-research | 4.60 | 25.00 | 38.89 | 36.11 |
| OpenAI-deepresearch | 5.00 | 0.00 | 100.00 | 0.00 |
| Gemini-2.5-Pro-deepresearch | 6.70 | 61.27 | 31.13 | 7.60 |
| WebWeaver(Qwen3-30B-A3B) | 4.57 | 28.65 | 34.90 | 36.46 |
| WebWeaver(Claude-Sonnet-4) | 6.96 | 66.86 | 10.47 | 22.67 |
| Enterprise-DR(Gemini-2.5-Pro) | 6.82 | 71.57 | 19.12 | 9.31 |
| RhinoInsigh(Gemini-2.5-Pro) | 6.82 | 68.51 | 11.02 | 20.47 |
| AgentCPM-Report | 6.60 | 57.60 | 13.73 | 28.68 |
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.
Acknowledgements
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 .
Contributions
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
Citation
If AgentCPM-Report is helpful for your research, please cite it as follows:
@software{AgentCPMReport2026,
title = {AgentCPM-Report: Gemini-2.5-pro-DeepResearch Level Local DeepResearch},
author = {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},
year = {2026},
url = {https://github.com/OpenBMB/AgentCPM}
}
Runs of openbmb AgentCPM-Report on huggingface.co
322
Total runs
0
24-hour runs
-34
3-day runs
-19
7-day runs
-4.4K
30-day runs
More Information About AgentCPM-Report huggingface.co Model
Url of AgentCPM-Report
AgentCPM-Report huggingface.co Url
Provider of AgentCPM-Report huggingface.co
Other API from openbmb
Updated:October 05 2025
Total runs:
127.1K
Run Growth:
19.2K
Growth Rate:
15.38%
Total runs:
117.8K
Run Growth:
4.9K
Growth Rate:
4.17%
Total runs:
68.6K
Run Growth:
192
Growth Rate:
0.28%
Total runs:
34.1K
Run Growth:
2.8K
Growth Rate:
8.34%
Total runs:
30.7K
Run Growth:
-1.4K
Growth Rate:
-4.66%
Total runs:
21.3K
Run Growth:
3.7K
Growth Rate:
17.32%
Total runs:
15.9K
Run Growth:
372
Growth Rate:
2.33%
Total runs:
11.3K
Run Growth:
-26.7K
Growth Rate:
-235.99%
Total runs:
8.3K
Run Growth:
499
Growth Rate:
5.99%
Total runs:
7.7K
Run Growth:
-4.1K
Growth Rate:
-52.99%
Total runs:
6.7K
Run Growth:
220
Growth Rate:
3.32%
Total runs:
5.2K
Run Growth:
3.2K
Growth Rate:
61.96%
Total runs:
4.6K
Run Growth:
1.9K
Growth Rate:
42.16%
Total runs:
4.1K
Run Growth:
1.2K
Growth Rate:
29.52%
Total runs:
3.4K
Run Growth:
-1.0K
Growth Rate:
-30.05%
Total runs:
3.1K
Run Growth:
135
Growth Rate:
4.37%
Total runs:
2.6K
Run Growth:
-49
Growth Rate:
-1.85%
Total runs:
2.6K
Run Growth:
-5.0K
Growth Rate:
-190.17%
Total runs:
2.2K
Run Growth:
-550
Growth Rate:
-25.47%
Total runs:
2.0K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.3K
Run Growth:
99
Growth Rate:
7.52%
Total runs:
1.3K
Run Growth:
1.0K
Growth Rate:
81.06%
Total runs:
1.1K
Run Growth:
877
Growth Rate:
80.83%
Total runs:
1.0K
Run Growth:
977
Growth Rate:
93.76%
Total runs:
1.0K
Run Growth:
900
Growth Rate:
87.12%
Total runs:
1.0K
Run Growth:
876
Growth Rate:
85.55%
Total runs:
879
Run Growth:
69
Growth Rate:
7.85%
Total runs:
802
Run Growth:
768
Growth Rate:
95.76%
Total runs:
708
Run Growth:
29
Growth Rate:
4.10%
Total runs:
610
Run Growth:
573
Growth Rate:
93.93%
Total runs:
331
Run Growth:
-791
Growth Rate:
-238.97%
Total runs:
329
Run Growth:
17
Growth Rate:
5.17%
Total runs:
288
Run Growth:
-63
Growth Rate:
-21.88%
Total runs:
229
Run Growth:
-397
Growth Rate:
-173.36%
Total runs:
227
Run Growth:
-56
Growth Rate:
-24.67%
Total runs:
200
Run Growth:
55
Growth Rate:
27.50%
Total runs:
193
Run Growth:
22
Growth Rate:
11.40%
Total runs:
112
Run Growth:
-22
Growth Rate:
-19.64%
Total runs:
91
Run Growth:
51
Growth Rate:
56.04%
Total runs:
71
Run Growth:
25
Growth Rate:
35.21%
Total runs:
69
Run Growth:
36
Growth Rate:
70.59%
Total runs:
52
Run Growth:
0
Growth Rate:
0.00%
Total runs:
44
Run Growth:
-3
Growth Rate:
-6.82%
Total runs:
37
Run Growth:
-1
Growth Rate:
-2.86%
Total runs:
34
Run Growth:
-2
Growth Rate:
-6.06%
Total runs:
28
Run Growth:
2
Growth Rate:
7.14%
Total runs:
27
Run Growth:
6
Growth Rate:
22.22%
Total runs:
26
Run Growth:
2
Growth Rate:
7.69%
Total runs:
26
Run Growth:
-33
Growth Rate:
-126.92%
Total runs:
19
Run Growth:
-18
Growth Rate:
-94.74%