# Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization

arXiv: https://arxiv.org/abs/2610.02366 · HTML: https://mlsanity.com/paper/2610.02366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 66 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://mlsanity.com/paper/2201.09863/) (2022)
- [Learning to Jump from Pixels](https://mlsanity.com/paper/2110.15344/) (2021)
- [FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control](https://mlsanity.com/paper/2505.22642/) (2025)
- [Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design](https://mlsanity.com/paper/2110.03659/) (2021)
- [Neural Graph Evolution: Towards Efficient Automatic Robot Design](https://mlsanity.com/paper/1906.05370/) (2019)
- [DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models](https://mlsanity.com/paper/2311.17053/) (2023)
- [Task-Agnostic Morphology Evolution](https://mlsanity.com/paper/2102.13100/) (2021)
- [Multi-Objective Graph Heuristic Search for Terrestrial Robot Design](https://mlsanity.com/paper/2107.05858/) (2021)
- [SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments](https://mlsanity.com/paper/2303.09555/) (2023)
- [Efficient automatic design of robots](https://mlsanity.com/paper/2306.03263/) (2023)
- [Functional Co-Optimization of Articulated Robots](https://mlsanity.com/paper/1707.06617/) (2017)
- [A Mathematical Theory of Co-Design](https://mlsanity.com/paper/1512.08055/) (2015)
- [VLMgineer: Vision Language Models as Robotic Toolsmiths](https://mlsanity.com/paper/2507.12644/) (2025)
- [Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design](https://mlsanity.com/paper/2402.15038/) (2024)
- [Convergent Functions, Divergent Forms](https://mlsanity.com/paper/2505.21665/) (2025)
- [House of Dextra: Cross-embodied Co-design for Dexterous Hands](https://mlsanity.com/paper/2512.03743/) (2025)
- [Natural Selection via Foundation Models for Soft Robot Evolution](https://mlsanity.com/paper/2503.02249/) (2025)
- [Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization](https://mlsanity.com/paper/2603.15388/) (2026)
- [Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design](https://mlsanity.com/paper/2607.25798/) (2026)
- [Agile legged locomotion in reconfigurable modular robots](https://mlsanity.com/paper/2505.00784/) (2025)
- [Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian Optimization](https://mlsanity.com/paper/2603.18408/) (2026)
- [Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.22748/) (2026)
- [BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI](https://mlsanity.com/paper/2609.03497/) (2026)
- [AthenaZero: A low-inertia, bimanual robot for dynamic manipulation](https://mlsanity.com/paper/2609.19194/) (2026)

## Abstract (arXiv)

Finding an optimal behaviour policy within a given environment is a widely studied problem in domains as diverse as games, robotics, energy infrastructure, communication networks, and multi-agent systems. Numerous benchmarks have been developed to support such research, but the vast majority assume that the agent's embodiment (design) is fixed, focusing instead on policy learning alone. Lifting this assumption gives rise to a broader class of problems in which optimizing embodiment and policy separately is highly suboptimal. An agent's embodiment strongly shapes which control policies can be discovered, while the optimal embodiment is in turn defined by the policies it admits. To help the research community study this class of problems explicitly and systematically, we introduce Co-Design Gym - a suite of benchmark environments for jointly optimizing embodiment and policy. Our environments span domains such as robotic manipulation and locomotion, multi-robot cooperation, deformable and soft dynamics, video games, electricity grids, wireless networks, F1 racing, multi-agent warehouses, and optimal control, offering 20 environment families (domains), with over 85 distinct co-design presets in total. We further contribute a systematic evaluation of representative co-design algorithms, characterizing the current state of the art. Together, these contributions lay the groundwork for cumulative, comparable progress in co-design.