arXiv cs.AI· Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang, Junfeng Yang, Shilong Liu·· 1 天前AI 评分48
EmbodiedRSI：通过假设引导的协同进化实现主动持续机器人学习
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
AI 导读
EmbodiedRSI 是一个自进化智能体框架，通过快慢双系统架构与假设图维护代码和技能假设，并用信息价值实验选择区分假设的物理实验。在 RoboCasa365 上达到 77.0% 整体成功率、Composite-Unseen 71.3%，远超最佳基线 40.1%；在 LIBERO-Pro 上达 86.8%。该框架还零样本迁移到真实机器人，在多项挑战性任务上取得 71.3% 整体成功率。
正文 · 原文
Abstract:Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes to pursue. We introduce EmbodiedRSI, a self-evolving agentic harness that autonomously decides where to explore next and turns the resulting physical interaction into improved code and skills. EmbodiedRSI realizes this through a Fast-Slow Dual-System Architecture, in which competing code and skill hypotheses are maintained in a Hypothesis Graph. Value-of-Information Experiment Selection chooses physical experiments that can distinguish these hypotheses. Their outcomes guide Code-Skill Co-Evolution. The Slow System builds Hierarchical Memory, and Reward-Grounded Memory Learning selects effective memory according to their value for later Fast-System improvement. On RoboCasa365, EmbodiedRSI reaches 77.0% overall success and 71.3% on Composite-Unseen, compared with 40.1% for the best baseline. EmbodiedRSI also reaches 86.8% overall success on LIBERO-Pro. Beyond benchmark performance, EmbodiedRSI transfers zero-shot to real-world robot, achieving 71.3% overall success across multiple challenging tasks.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.10498 [cs.AI] |
| (or arXiv:2610.10498v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10498 arXiv-issued DOI via DataCite |
Submission history
From: Python Song [view email]
[v1]
Wed, 7 Oct 2026 17:48:02 UTC (4,283 KB)
[v2]
Thu, 12 Nov 2026 04:07:56 UTC (5,228 KB)
来源：arXiv cs.AI · arxiv.org