# EmbodiedRSI：通过假设引导的协同进化实现主动持续机器人学习

> 原文链接：https://robotics.hellobike.com/papers/2026-10-07-2610-10498
> 频道：papers | 更新日期：2026-10-07 | 标签：arxiv, cs.RO
> 核心摘要：提出EmbodiedRSI，自主选择物理实验并将交互转化为代码和技能改进，在RoboCasa365、LIBERO-Pro及真实机器人验证。

# EmbodiedRSI：通过假设引导的协同进化实现主动持续机器人学习

::: v-pre
> 原文链接：[EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution](https://arxiv.org/abs/2610.10498)（arXiv 2610.10498 · 发布日期：2026-10-07）

**EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution**

提出EmbodiedRSI，自主选择物理实验并将交互转化为代码和技能改进，在RoboCasa365、LIBERO-Pro及真实机器人验证。

## 核心要点

- 机器人基础模型在物体位置或任务指令变化时性能可能下降，后训练数据采集成本高。
- EmbodiedRSI以快慢双系统维护假设图，用信息价值选择实验并推动代码-技能协同进化。
- 慢系统构建层级记忆，并以奖励为依据选择有助于后续快系统改进的记忆。
- 在RoboCasa365总体成功率77.0%，LIBERO-Pro总体86.8%，并零样本迁移到真实机器人。

**验证范围与局限**：验证范围包括RoboCasa365、LIBERO-Pro基准，以及真实世界机器人上的多个挑战任务。

## 英文摘要 (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.

作者：Python Song, Zhixuan Liang, Fu Kelsey, Mengdi Wang, Junfeng Yang, Shilong Liu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.10498：EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution](https://arxiv.org/abs/2610.10498)