Introduction

MiroThinker v1.5 is the world-leading search agent designed to advance tool-augmented reasoning and information-seeking capabilities.

Unlike previous agents that scale only model size or context length, MiroThinker introduces interactive scaling at the agent level, systematically training the agent to handle deeper and more frequent agent–environment interactions as a third dimension of performance improvement. Interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories.

Empirical results demonstrate the effectiveness of this interactive scaling. Performance across several benchmarks improves predictably as the agent engages in increasingly deep and frequent interactions with its environment.

👁 image

Key Features

• MiroThinker v1.5 supports a 256K context window, long-horizon reasoning, and deep multi-step analysis.
• Handles up to 400 tool calls per task — a substantial improvement over previous open-source research agents.
• Released in 30B and 235B parameter scales, accompanied by a comprehensive suite of tools and workflows to flexibly support diverse research settings and compute budgets.

MiroThinker v1.5 demonstrates strong general-research performance across a broad range of benchmarks, achieving 39.2%, 69.8%, 71.5%, and 80.8% on HLE-Text, BrowseComp, BrowseComp-ZH, and GAIA-Val-165, respectively. These results surpass previous open-source agents and set the new world-leading BrowseComp performance.

👁 image

More details can be found in our .

Online Demo

Welcome to try out our online demo DR MiroMind which offers agentic general QA experience better than OpenAI DeepResearch.

Note: This demo is not intended for BrowseComp evaluation. Each query is limited to 100 tool calls for latency and stability. BrowseComp involves long-horizon tasks that typically require over 200 tool calls for our agent, which is outside the scope of this demo.

Performance

To prevent potential information leakage (e.g., searching benchmark answers from HuggingFace), access to HuggingFace has been explicitly disabled in these tools.

We further perform canary string testing on the tool outputs of all trajectories and disregard any trajectory found to be contaminated, treating it as an incorrect answer.

Quick Start

For optimal usage, we recommend using MiroThinker with our tool-enabled agent framework and thinking mode enabled. Please refer to our GitHub repository for installation instructions, examples, and full documentation:

👉 https://github.com/MiroMindAI/MiroThinker

Local Deployment

It is recommended to use SGLang or vLLM for deploying the agent:

# SGLang
python -m sglang.launch_server --model-path miromind-ai/MiroThinker-v1.5-235B --tp 8 --host 0.0.0.0 --port 1234
# vLLM
vllm serve miromind-ai/MiroThinker-v1.5-235B --tensor-parallel-size 8 --max-model-len 262144 --enable-reasoning

For optimal performance in agentic tasks, we recommend the following inference parameters:

temperature: 1.0
top_p: 0.95
repetition_penalty: 1.05
max_context_length: 262144
max_tokens: 16384

Recommended System Prompt

We use this unified XML-wrapped JSON format to describe and organize all tools. If you have additional tools, please document them using the same structure and formatting to ensure consistent parsing, compatibility, and optimal performance across the environment.

Minimal Runnable Example

The following example shows how to run a MCP-style tool-calling workflow, including system prompt generation, agent invocation, tool execution, and final response generation.

Before running the script, make sure to set the required environment variables:

export OPENAI_API_KEY="your-api-key-here"
export BASE_URL="https://your-agent-endpoint.example.com/v1"

License

MiroThinker v1.5 is released under the MIT License.

Citation

If you find this project useful in your research, please consider citing:

@article{miromind2025mirothinker,
 title={MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling},
 author={MiroMind Team and Bai, Song and Bing, Lidong and Chen, Carson and Chen, Guanzheng and Chen, Yuntao and Chen, Zhe and Chen, Ziyi and Dong, Xuan and others},
 journal={arXiv preprint arXiv:2511.11793},
 year={2025}
}

Contact Us

MiroThinker is developed by the MiroMind AI Team. If you would like to leave us a message, feel free to get in touch. In addition to GitHub, Discord, WeChat, and RedNote, you can also reach us via email at service@miromind.ai.

Base model