InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation
- 类型：arxiv
- 标识：2610.02196
- 链接：https://arxiv.org/abs/2610.02196
- 主分类：engineering
- 形态：method
- TLDR：We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining. Our key insight is that a broad controller already holds much of the competence a new task needs, and that this competence becomes accessible through an interface between planning and control that is expressive enough to specify contact-rich, multi-stage interactions, yet executable and measurable enough that execution feedback can guide planning from experience.
- 待LLM分类：是
- 来源文件：
- /inbox/tom/_candidates/2026-10-02-agent-rag-longcontext-candidates.json