# Natural Selection via Foundation Models for Soft Robot Evolution

arXiv: https://arxiv.org/abs/2503.02249 · HTML: https://mlsanity.com/paper/2503.02249/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 38 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 7 of 7)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://mlsanity.com/paper/2201.09863/) (2022)
- [Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks](https://mlsanity.com/paper/2312.06876/) (2023)

## Built on by (most cited first, 4 of 4)

- [VLMgineer: Vision Language Models as Robotic Toolsmiths](https://mlsanity.com/paper/2507.12644/) (2025)
- [When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills](https://mlsanity.com/paper/2605.25832/) (2026)
- [RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots](https://mlsanity.com/paper/2609.29490/) (2026)
- [Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization](https://mlsanity.com/paper/2610.02366/) (2026)

## Abstract (arXiv)

Designing soft robots is a complex and iterative process that demands cross-disciplinary expertise in materials science, mechanics, and control, often relying on intuition and extensive experimentation. While foundation models, especially Large Language Models (LLMs), have demonstrated impressive reasoning abilities, their capacity to conduct embodied design remains largely unexplored. This paper introduces RoboCrafter-QA, a novel benchmark to evaluate whether LLMs can learn representations of soft robot designs that effectively bridge the gap between high-level task descriptions and low-level morphological and material choices. RoboCrafter-QA leverages the EvoGym simulator to generate a diverse set of soft robot design challenges, spanning robotic locomotion, manipulation, and balancing tasks. Our experiments with SOTA multi-modal LLMs reveal that while these models exhibit promising capabilities in learning design representations, they struggle with fine-grained distinctions between designs with subtle performance differences. To overcome these limitations, we finetune an efficient, open-source LLM that achieves SOTA performance on our benchmark, demonstrating superior capabilities in both design selection and direct generation of high-performing robot morphologies. Furthermore, we construct a physical replica of the modular soft robot and demonstrate a strong sim-to-real correlation, validating that superior benchmark performance has the potential to translate to effective real-world design selection. Our full system will be open-sourced to foster this exciting direction.