# iAm.md：面向未知开放词汇域的通过智能体内省实现机器人技能自评

> 原文链接：https://robotics.hellobike.com/papers/2026-10-07-2610-10962
> 频道：papers | 更新日期：2026-10-07 | 标签：arxiv, cs.RO
> 核心摘要：针对具身任务中的 grounding failure，iAm.md 用 Markdown 标准结合部署证据与开放词汇语义映射，在模拟 TIAGo 导航操纵任务上验证。

# iAm.md：面向未知开放词汇域的通过智能体内省实现机器人技能自评

::: v-pre
> 原文链接：[iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains](https://arxiv.org/abs/2610.10962)（arXiv 2610.10962 · 发布日期：2026-10-07）

**iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains**

针对具身任务中的 grounding failure，iAm.md 用 Markdown 标准结合部署证据与开放词汇语义映射，在模拟 TIAGo 导航操纵任务上验证。

## 核心要点

- 大模型生成机器人行为时，可能未确认机器人与环境是否支持请求操作。
- iAm.md 提出 Markdown 标准与生成框架，用部署证据锚定代码生成式行为生成。
- 方法结合视觉语言检测与目标分割，并关联到持久对象记录以支持智能体内省。
- 在模拟 TIAGo 的导航与操纵任务中，展示其支持技能自评和可执行任务泛化。

**验证范围与局限**：验证范围为仿真中的 TIAGo 机器人导航与操纵任务。

## 英文摘要 (Abstract)

Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied agents based on Foundation models can generate plausible plans in autonomous robotics scenarios. Due to limited context windows or hallucinatory phenomena in the next-token prediction formulation, behaviors may be generated without establishing whether the deployed robot and the observed environment actually support the requested operation, in what we call a "grounding failure". Thanks to the recent improvements in reasoning capabilities of foundation models, autonomous robot behavior generation problem can be formulated as a code generation problem. We present iAm.md, a Markdown standard and generation framework, that allows anchoring this process in complementary forms of deployment evidence. Through open-vocabulary semantic mapping, we combine local vision-language detections and object segmentation and refer them to persistent object records in this intermediate standardized representation, allowing agentic introspection. We then study this new technique on a simulated TIAGo, on navigation-and-manipulation tasks, showing how this standardized representation jointly supports skill self-assessment and executable task generalization.

作者：Vincenzo Guarino, Emanuele Musumeci, Vincenzo Suriani, Daniele Nardi
:::

## 原始参考来源 (Sources)

- [arXiv 2610.10962：iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains](https://arxiv.org/abs/2610.10962)