When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910255268495360 |
|---|---|
| author | Wang, Yunfei Xu, Xiaohao Li, Yang Huang, Xiaonan |
| author_facet | Wang, Yunfei Xu, Xiaohao Li, Yang Huang, Xiaonan |
| contents | Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library. Each skill stores a structural archetype, evidence-grounded positive and negative rules, and the evaluated designs that support them, making design memory inspectable rather than implicit in a population. During search, the agent retrieves skills to condition LLM edits of elite bodies while retaining a Genetic Algorithm (GA) mutation path for exploration; after evaluation, it updates the library through Add, Diagnose, and Merge. Across seven EvoGym tasks spanning locomotion, traversal, and object interaction, Auto-Robotist improves cold-start 5x5 search and transfers learned skills to 10x10 design spaces, where reference-conditioned transfer outperforms GA on every task. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25832 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills Wang, Yunfei Xu, Xiaohao Li, Yang Huang, Xiaonan Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search traces into an explicit natural-language skill library. Each skill stores a structural archetype, evidence-grounded positive and negative rules, and the evaluated designs that support them, making design memory inspectable rather than implicit in a population. During search, the agent retrieves skills to condition LLM edits of elite bodies while retaining a Genetic Algorithm (GA) mutation path for exploration; after evaluation, it updates the library through Add, Diagnose, and Merge. Across seven EvoGym tasks spanning locomotion, traversal, and object interaction, Auto-Robotist improves cold-start 5x5 search and transfers learned skills to 10x10 design spaces, where reference-conditioned transfer outperforms GA on every task. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code will be released upon acceptance. |
| title | When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills |
| topic | Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.25832 |