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.

翻译：大语言模型（LLM）正越来越多地被用作进化机器人设计的方案生成器，然而大多数循环过程仍是无记忆的：模拟器结果塑造了下一代种群，但并未作为可复用的设计知识加以保存。我们提出Auto-Robotist——一种自我进化的LLM代理，它将形态搜索轨迹提炼为明确的自然语言技能库。每项技能存储一种结构原型、基于证据的正反规则以及支撑这些规则的经验证设计，从而使设计记忆可被审查而非隐含在种群之中。在搜索过程中，代理检索技能以条件化LLM对精英个体的编辑，同时保留遗传算法（GA）变异路径以维持探索能力；评估后，通过添加、诊断与合并操作更新技能库。在涵盖运动、穿越和物体交互的七项EvoGym任务中，Auto-Robotist既改善了冷启动的5x5搜索，又将所学技能迁移至10x10设计空间，其中基于参考条件的迁移在每项任务上均优于GA。这些结果表明，LLM代理能够将昂贵的物理评估转化为可复用、可审计的设计原则。我们的代码将在论文接收后开源。