eubiota-planner-8b

<div style="display: flex; align-items: center; justify-content: center; gap: 8px;"> <a href="https://eubiota.ai/"> <img src="https://huggingface.co/datasets/Eubiota/microbio-bench/resolve/main/logo_transparent.png" alt="Eubiota Logo" style="height: 84px; width: auto;"> </a> </div> <div align="center"> <a href="https://x.com/lupantech/status/2028873916966703343"><img src="https://img.shields.io/badge/Twitter-000000?style=for-the-badge&logo=X&logoColor=white" alt="X"></a> <a href="https://discord.gg/GCEFSN2RWJ"><img src="https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a> <a href="https://eubiota.ai/"><img src="https://img.shields.io/badge/Website-50C878?style=for-the-badge&logo=google-chrome&logoColor=white" alt="Website"></a> <a href="https://www.biorxiv.org/content/10.64898/2026.02.27.708412v1"><img src="https://img.shields.io/badge/bioRxiv-Paper-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white" alt="Paper"></a> <a href="https://app.eubiota.ai/"><img src="https://img.shields.io/badge/App-FF9500?style=for-the-badge&logo=react&logoColor=white" alt="App"></a> <a href="https://github.com/lupantech/Eubiota"><img src="https://img.shields.io/badge/GitHub-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub"></a> <a href="https://huggingface.co/datasets/Eubiota/microbio-bench"><img src="https://img.shields.io/badge/Dataset-FFB7B2?style=for-the-badge&logo=huggingface&logoColor=white" alt="Dataset"></a> </div> <p align="center"> 🤗 <a href="https://huggingface.co/Eubiota" target="_blank">HuggingFace</a> ｜ 🌐 <a href="https://eubiota.ai/" target="_blank">Website</a> ｜ 📄 <a href="https://www.biorxiv.org/content/10.64898/2026.02.27.708412v1" target="_blank">Paper</a> ｜ 💻 <a href="https://github.com/lupantech/Eubiota" target="_blank">GitHub</a> ｜ 🚀 <a href="https://app.eubiota.ai/" target="_blank">App</a> </p>

---

Eubiota-Planner-8B is a specialized 8-billion parameter language model fine-tuned for autonomous microbiome discovery. It serves as the core planner module in the Eubiota agentic AI framework, orchestrating multi-agent reasoning and tool-grounded scientific exploration.

Model Description

Intended Use

Primary Use Cases

• Microbiome Hypothesis Generation: Formulating mechanistic hypotheses about host-microbe interactions
• Experimental Design: Planning and orchestrating scientific workflows for microbiome research
• Multi-Tool Coordination: Selecting and sequencing domain-specific tools (PubMed, KEGG pathways, etc.) for complex scientific queries

Training

Training Data

The model was trained on a mixture of four domain datasets:

Training Method

The model is trained using GRPO-MAS (Group Relative Policy Optimization for Multi-Agent Systems), a reinforcement learning approach designed for multi-agent coordination. This method enables the planner to learn effective tool selection and sequencing strategies through outcome-driven refinement.

Integrated Tools

Eubiota-Planner-8B orchestrates 18 domain-specific tools spanning web and literature search, biological databases, laboratory resources, and computation utilities.

Benchmark Suite

Eubiota-Planner-8B is evaluated on six benchmarks across two categories to assess both broad biomedical competence and microbiome-specific mechanistic reasoning.

General Biomedical Competence

Microbiome-Specific Mechanistic Reasoning

Four domain-specific benchmarks derived from MDIPID emphasizing mechanistic linking among microbes, drugs, host pathways, and genes:

Acknowledgements

<div style="display: flex; align-items: center; justify-content: center; gap: 8px;"> <a href="https://chanzuckerberg.com/" style="flex-shrink: 0;"> <img src="assets/logos/chan_zuckberg.svg" style="height: 75px; width: auto;" alt="Chan Zuckerberg Initiative"> </a> <a href="https://hai.stanford.edu/" style="flex-shrink: 0;"> <img src="assets/logos/stanford_hai.png" style="height: 76px; width: auto;" alt="Stanford HAI"> </a> <a href="https://www.renaissancephilanthropy.org/" style="flex-shrink: 0;"> <img src="assets/logos/Renaissance.png" style="height: 84px; width: auto;" alt="Renaissance Philanthropy"> </a> <a href="https://deepmind.google/technologies/gemini/" style="flex-shrink: 0;"> <img src="assets/logos/Gemini.png" style="height: 84px; width: auto;" alt="Google Gemini"> </a> </div>

We also thank the following open-source projects:

• VeRL for the excellent RL framework design.
• vLLM for fast LLM inference support.
• AgentFlow and Agent Lightning for early-stage exploration in multi-agent RL training.

Citation

@article{lu2026eubiota,
  title = {Eubiota: Modular Agentic AI for Autonomous Discovery in the Gut Microbiome},
  author = {Lu, Pan and Gao, Yifan and Peng, William G. and Zhang, Haoxiang and Zhu, Kunlun and Robinson, Elektra K. and Xu, Qixin and Kotaka, Masakazu and Zhang, Harrison G. and Li, Bingxuan and Shiver, Anthony L. and Choi, Yejin and Huang, Kerwyn Casey and Sonnenburg, Justin and Zou, James},
  journal = {bioRxiv},
  year = {2026},
  month = {feb},
  day = {27},
  doi = {10.64898/2026.02.27.708412},
  url = {https://www.biorxiv.org/content/10.64898/2026.02.27.708412v1},
  publisher = {Cold Spring Harbor Laboratory}
}