ExoMind: Democratizing Scientific Intelligence via Extended-Mind-Inspired Agentic System

Name: ExoMind-9B
Rating: 2.5 (24 reviews)

ExoMind Team · Shanghai Artificial Intelligence Laboratory

Project Page

Technical Report PDF

Hugging Face

GitHub

🔥 News

2026.8.25: 🔥 We have released a series of official GGUF variants for ExoMind and ExoMind-9B. Please refer to the ExoMind collection. We also thank mradermacher for providing additional GGUF quantizations, including both static and importance-matrix variants: ExoMind-i1-GGUF, ExoMind-GGUF, ExoMind-9B-i1-GGUF, and ExoMind-9B-GGUF.
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 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.

🥇 Best score among the representative models shown

Benchmark	⭐ Ours	Representative frontier models
ExoMind 35B-A3B	Claude-Opus-4.8 Thinking	GPT-5.5 (xhigh)	Gemini-3.1-Pro Preview	Kimi-K3	Qwen3.7-Max	GLM-5.2	DeepSeek-V4-Pro (Max)
🧪 Scientific Research
HLE w/ tools	56.8	🥇 57.9	52.2	51.4	56.0	53.5	54.7	48.2
FrontierScience-Research	🥇 70.0	26.7	26.7	11.7	21.7	10.0	15.0	13.3
CMT-Benchmark	🥇 84.0	46.0	43.0	43.0	34.0	34.0	20.0	28.0
CritPt	25.7	20.9	🥇 27.1	17.7	23.4	13.4	20.9	7.1
🧠 Scientific Reasoning
AMO-Bench	🥇 78.0	74.0	70.0	63.1	64.0	57.4	54.0	68.0
IMO-AnswerBench	🥇 92.8	86.8	83.8	90.0	82.8	90.0	91.0	89.8
HiPhO	🥇 49.7	46.4	43.3	43.4	42.4	38.8	37.4	38.7
FrontierScience-Olympiad	🥇 89.0	75.0	78.0	77.0	69.0	80.0	76.5	76.0
Eight-benchmark average	🥇 68.3	54.2	53.0	49.7	49.2	47.1	46.2	46.1

Complete settings and comparisons are available in the evaluation explorer.

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. See 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}
}