# StateSkill-Agent：通过状态条件技能实现高效有效的具身智能体

> 原文链接：https://robotics.hellobike.com/papers/2026-10-10-2610-14601
> 频道：papers | 更新日期：2026-10-10 | 标签：arxiv, cs.RO
> 核心摘要：该工作面向具身MLLM智能体任务求解，提出StateSkill及演化优化机制，并在多种具身任务上验证。

# StateSkill-Agent：通过状态条件技能实现高效有效的具身智能体

::: v-pre
> 原文链接：[StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill](https://arxiv.org/abs/2610.14601)（arXiv 2610.14601 · 发布日期：2026-10-10）

**StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill**

该工作面向具身MLLM智能体任务求解，提出StateSkill及演化优化机制，并在多种具身任务上验证。

## 核心要点

- 目标是让具身MLLM智能体学习、抽象并复用可迁移、可泛化的行为模式。
- StateSkill将具身交互经验建模为有限状态机，按任务进展状态组织技能与指导。
- StateSkill-Evolve通过回顾成功和失败的状态引导轨迹，迭代细化StateSkill。
- StateGRPO把StateSkill演化与状态条件GRPO模型优化统一到迭代学习循环中。

**验证范围与局限**：验证范围为多种具身任务；摘要未说明仿真或真机等具体设置。

## 英文摘要 (Abstract)

In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable and generalizable behavioral patterns. To this end, we propose StateSkill, a new skill representation for embodied agents, which introduces the concept of "finite-state machines" into skill modeling for effective and efficient skill construction and learning. The core idea of StateSkill is to model embodied interaction experiences as a finite-state machine, where a skill is organized around a set of task-progress states, state transitions, and state-conditioned guidance, enabling embodied agents to dynamically adjust their skills as the task progresses while keeping skill contexts compact and stage-relevant. We further develop StateSkill-Evolve, an experience-driven evolution mechanism that iteratively refines StateSkill through retrospective analysis of new successful and failed state-guided trajectories. Upon this, we introduce StateGRPO, which integrates StateSkill evolution and model optimization via state-conditioned GRPO into a unified iterative learning loop, enabling state-conditioned skills and model capabilities to co-evolve and reinforce each other. Extensive experiments demonstrate the effectiveness of our proposed methods and trained model (i.e., StateSkill-Agent) across various embodied tasks.

作者：Changxu Wei, Jingyi Zhang, Zhiyu Zheng, Tianyi Lin, Yixian Zhang, Yunpeng Qing, Jingyuan Liu, Zhi Hou, Jiaxing Huang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.14601：StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill](https://arxiv.org/abs/2610.14601)