Self-Evolving Embodied Agents via Skill-Harness Evolution

• 类型：arxiv
• 标识：2608.11350
• 链接：https://arxiv.org/abs/2608.11350
• 主分类：agent
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This work proposes SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen and improves the non-parametric agent system by evolving reusable skills and a context-code harness through target-environment rollouts.
• 副分类：evaluation
• 待LLM分类：否
• 标题中文：基于 Skill-Harness 演化的自演化具身智能体
• TLDR中文：本文提出 SHAPER，一种免训练具身自适应的自演化框架，保持模型参数冻结，通过目标环境 rollout 演化可复用的 skills 和 context-code harness 来改进非参数化 Agent 系统。
• 来源文件：
• /inbox/tom/_candidates/2026-08-13-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-08-14-agent-rag-longcontext-candidates.json
• [S2 enrich]