README.md

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
base_model_relation: finetune
pipeline_tag: image-text-to-text
language:
- en
- zh
tags:
- exomind
- scientific-reasoning
- scientific-research
- agentic
- tool-use
- multimodal
- vision-language
- qwen3.5
- safetensors
---

<div align="center">

<img src="./assets/ExoMind.png" alt="ExoMind" width="560">

# ExoMind-9B

**A compact checkpoint from ExoMind: Democratizing Scientific Intelligence via Extended-Mind-Inspired Agentic System**

**ExoMind Team · Shanghai Artificial Intelligence Laboratory**

<p>
  <a href="https://ai4sgi.github.io/ExoMind/">
    <img src="https://img.shields.io/badge/Project_Page-Visit-174F87?style=for-the-badge&logo=googlechrome&logoColor=white" alt="Project Page">
  </a>
  <a href="https://github.com/AI4SGI/ExoMind/blob/main/Paper.pdf">
    <img src="https://img.shields.io/badge/Technical_Report-PDF-B31B1B?style=for-the-badge&logo=adobeacrobatreader&logoColor=white" alt="Technical Report PDF">
  </a>
</p>
<p>
  <a href="https://huggingface.co/AI4SGI/ExoMind-9B">
    <img src="https://img.shields.io/badge/Hugging_Face-Model-FFD21E?style=for-the-badge&logo=huggingface&logoColor=000000" alt="Hugging Face">
  </a>
  <a href="https://github.com/AI4SGI/ExoMind">
    <img src="https://img.shields.io/badge/GitHub-Code-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub">
  </a>
  <a href="https://modelscope.cn/models/AI4SGI/ExoMind-9B">
    <img src="https://img.shields.io/badge/ModelScope-Model-624AFF?style=for-the-badge" alt="ModelScope">
  </a>
</p>

</div>

## 🔥 News

- **2026-08-12**: 🔥 We release the ExoMind technical report, official project page,
  and public repository.

## Overview

ExoMind-9B is the compact ExoMind checkpoint, fine-tuned from
[Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for lower-resource
experimentation in scientific reasoning and agentic research. It follows the
same extended-mind-inspired approach, organizing the model, specialized
interaction objects, and autonomous interaction processes as one system.

## Highlights

- **Compact scientific checkpoint:** supports resource-conscious experiments
  with the ExoMind reasoning and interaction paradigm.
- **Scientific interaction:** works with source discovery, evidence grounding,
  executable verification, and observation integration workflows.
- **Progressive CoI training:** develops intrinsic reasoning and interaction
  behavior from selected pure-reasoning and interaction trajectories.
- **Multimodal foundation:** retains the image-text capabilities of its Qwen3.5
  base model.

## Quick Start

Use a recent vLLM or SGLang release with Qwen3.5 support. The examples below
use the checkpoint's configured maximum context length of 262,144 tokens.

### vLLM

```bash
vllm serve AI4SGI/ExoMind-9B \
  --port 8000 \
  --tensor-parallel-size 1 \
  --max-model-len 262144 \
  --reasoning-parser qwen3 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder
```

### SGLang

```bash
python -m sglang.launch_server \
  --model-path AI4SGI/ExoMind-9B \
  --host 0.0.0.0 \
  --port 8000 \
  --tp-size 1 \
  --context-length 262144 \
  --reasoning-parser qwen3 \
  --tool-call-parser qwen3_coder
```

### OpenAI-Compatible API

```python
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
    model="AI4SGI/ExoMind-9B",
    messages=[
        {
            "role": "user",
            "content": "Develop a testable hypothesis and a rigorous verification plan for: ...",
        }
    ],
    temperature=1.0,
    top_p=0.95,
    extra_body={"top_k": 20},
)
print(response.choices[0].message.content)
```

## Evaluation

The table below reports the main ExoMind 35B-A3B system. ExoMind-9B is provided
as a compact checkpoint and has not been assigned these scores.

<p>
🥇 Best score among the representative models shown
</p>

<table>
<thead>
<tr>
<th rowspan="2" align="left">Benchmark</th>
<th align="center">⭐ Ours</th>
<th colspan="7" align="center">Representative frontier models</th>
</tr>
<tr>
<th align="center">ExoMind<br>35B-A3B</th>
<th align="center">Claude-Opus-4.8<br>Thinking</th>
<th align="center">GPT-5.5<br>(xhigh)</th>
<th align="center">Gemini-3.1-Pro<br>Preview</th>
<th align="center">Kimi-K3</th>
<th align="center">Qwen3.7-Max</th>
<th align="center">GLM-5.2</th>
<th align="center">DeepSeek-V4-Pro<br>(Max)</th>
</tr>
</thead>
<tbody>
<tr><td colspan="9" align="left"><b>🧪 Scientific Research</b></td></tr>
<tr><td align="left">HLE w/ tools</td><td align="center">50.9</td><td align="center">🥇 57.9</td><td align="center">52.2</td><td align="center">51.4</td><td align="center">56.0</td><td align="center">53.5</td><td align="center">54.7</td><td align="center">48.2</td></tr>
<tr><td align="left">FrontierScience-Research</td><td align="center">🥇 70.0</td><td align="center">26.7</td><td align="center">26.7</td><td align="center">11.7</td><td align="center">21.7</td><td align="center">10.0</td><td align="center">15.0</td><td align="center">13.3</td></tr>
<tr><td align="left">CMT-Benchmark</td><td align="center">🥇 84.0</td><td align="center">46.0</td><td align="center">43.0</td><td align="center">43.0</td><td align="center">34.0</td><td align="center">34.0</td><td align="center">20.0</td><td align="center">28.0</td></tr>
<tr><td align="left">CritPt</td><td align="center">25.7</td><td align="center">20.9</td><td align="center">🥇 27.1</td><td align="center">17.7</td><td align="center">23.4</td><td align="center">13.4</td><td align="center">20.9</td><td align="center">7.1</td></tr>
<tr><td colspan="9" align="left"><b>🧠 Scientific Reasoning</b></td></tr>
<tr><td align="left">AMO-Bench</td><td align="center">🥇 78.0</td><td align="center">74.0</td><td align="center">70.0</td><td align="center">63.1</td><td align="center">64.0</td><td align="center">57.4</td><td align="center">54.0</td><td align="center">68.0</td></tr>
<tr><td align="left">IMO-AnswerBench</td><td align="center">🥇 92.8</td><td align="center">86.8</td><td align="center">83.8</td><td align="center">90.0</td><td align="center">82.8</td><td align="center">90.0</td><td align="center">91.0</td><td align="center">89.8</td></tr>
<tr><td align="left">HiPhO</td><td align="center">🥇 49.7</td><td align="center">46.4</td><td align="center">43.3</td><td align="center">43.4</td><td align="center">42.4</td><td align="center">38.8</td><td align="center">37.4</td><td align="center">38.7</td></tr>
<tr><td align="left">FrontierScience-Olympiad</td><td align="center">🥇 89.0</td><td align="center">75.0</td><td align="center">78.0</td><td align="center">77.0</td><td align="center">69.0</td><td align="center">80.0</td><td align="center">76.5</td><td align="center">76.0</td></tr>
<tr><td align="left"><b>Eight-benchmark average</b></td><td align="center">🥇 67.5</td><td align="center">54.2</td><td align="center">53.0</td><td align="center">49.7</td><td align="center">49.2</td><td align="center">47.1</td><td align="center">46.2</td><td align="center">46.1</td></tr>
</tbody>
</table>

Complete settings and comparisons are available in the [evaluation
explorer](https://ai4sgi.github.io/ExoMind/#results).

## Intended Use

ExoMind-9B is intended for scientific question answering, mathematical and
computational reasoning, tool-use experiments, code-assisted verification, and
resource-conscious agentic prototypes.

## License and Attribution

The distributed checkpoint and upstream Qwen3.5 materials are provided under
the Apache License 2.0 included in this repository. The technical report,
scientific figures and results, and ExoMind brand assets are subject to the
[ExoMind Research Content and Brand Terms](./CONTENT_RIGHTS.md). See
[NOTICE.md](./NOTICE.md) for third-party notices.

## Citation

```bibtex
@misc{exomind2026,
  title  = {ExoMind: Democratizing Scientific Intelligence via Extended-Mind-Inspired Agentic System},
  author = {Peng Ye and Zhuo Liu and Jingqi Ye and Fangchen Yu and Shengji Tang and Yichen Jiang and Haonan He and Zongsheng Cao and Tao Chen and Bo Zhang and Wanli Ouyang and Bowen Zhou and Lei Bai},
  year   = {2026},
  note   = {Technical report},
  url    = {https://github.com/AI4SGI/ExoMind/blob/main/Paper.pdf}
}
```