@inproceedings{wang-etal-2026-search,
title = "When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills",
author = "Wang, Yunfei and
Xu, Xiaohao and
Li, Yang and
Huang, Xiaonan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.368/",
pages = "8417--8436",
ISBN = "979-8-89176-459-0",
abstract = "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 $5\times5$ search and transfers learned skills to $10\times10$ design spaces, where reference-conditioned transfer outperforms or matches GA on every task when averaged across seeds. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code is publicly available at https://github.com/wangyf9/Auto-Robotist."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-search">
<titleInfo>
<title>When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunfei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaonan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>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 5\times5 search and transfers learned skills to 10\times10 design spaces, where reference-conditioned transfer outperforms or matches GA on every task when averaged across seeds. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code is publicly available at https://github.com/wangyf9/Auto-Robotist.</abstract>
<identifier type="citekey">wang-etal-2026-search</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.368/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8417</start>
<end>8436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills
%A Wang, Yunfei
%A Xu, Xiaohao
%A Li, Yang
%A Huang, Xiaonan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-search
%X 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 5\times5 search and transfers learned skills to 10\times10 design spaces, where reference-conditioned transfer outperforms or matches GA on every task when averaged across seeds. These results suggest that LLM agents can convert expensive physical evaluations into reusable, auditable design principles. Our code is publicly available at https://github.com/wangyf9/Auto-Robotist.
%U https://aclanthology.org/2026.emnlp-main.368/
%P 8417-8436
Markdown (Informal)
[When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills](https://aclanthology.org/2026.emnlp-main.368/) (Wang et al., EMNLP 2026)
ACL