MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics

🌐 Project Website | 📚 Documentation | 🤗 Weights and Data | 📄 Paper

MESA is a framework for building, scaling, and evaluating language-conditioned tabletop manipulation policies. The project includes:

• MESA-Gen for scalable task and demonstration generation.
• MESA-Bench for standardized evaluation across in-distribution, spatial, category, instance, and compositional generalization settings.

Installation

MESA uses uv for environment and dependency management.

1. Install uv using the official guide: https://docs.astral.sh/uv/getting-started/installation/
2. Clone the public repository:

   git clone https://github.com/pairlab/mesa-env.git mesa
   cd mesa

3. Sync dependencies from the repository root:

   uv sync

4. Optional: install LeRobot export dependencies:

   uv sync --extra lerobot

5. Run setup scripts (configures robosuite and downloads the simulation assets and the fixed evaluation initial states from Hugging Face):

   ./scripts/setup.sh

For detailed setup instructions, see docs/getting_started/installation.md.

Acknowledgements

MESA builds on top of and draws inspiration from the following projects:

• MimicLabs
• MimicGen
• OpenPI
• LeRobot
• RoboCasa
• LIBERO
• tyro

See docs/other/acknowledgement.md for the documentation version of this list.

Citation

If you find MESA useful in your research, please cite:

@inproceedings{
wilcox2026mesa,
title={{MESA}: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics},
author={Wilcox, Albert and Chang, Frank and Nguyen, Nhi and Chakraborty, Aishani and Collins, Jeremy A. and Saxena, Vaibhav and Joffe, Benjamin and Karamcheti, Siddharth and Garg, Animesh},
booktitle={10th Annual Conference on Robot Learning},
year={2026},
url={https://openreview.net/forum?id=Br2rXixvyN}
}

License

This repository is released under the MIT License. See LICENSE for full terms.