让机器人像程序员一样工作，靠工具组合完成复杂任务。
Towards the Harness of Embodied Agents
- 用可调用工具构建机器人智能循环，类比编程中的代理框架。
- 引入场景图与退出码机制，解决物理世界状态感知与动作评估难题。
- 适合研究具身智能、机器人系统设计的开发者与研究人员。
编码代理的成功确立了‘框架’范式：智能体的能力不仅取决于模型本身，更依赖其周围基础设施。我们探讨这一范式是否适用于物理世界的具身智能体。本文提出Thea框架，通过一个代理循环协调机器人能力，将各项功能封装为可调用工具。该框架继承编码代理的核心组件，并根据物理世界需求进行改造。然而，物理世界缺乏软件环境中免费提供的两个能力：读取世界状态和判断动作结果。为弥补此缺口，Thea引入“场景图作为上下文”，构建持久、符号化的世界表示；并引入“评估作为退出码”，用于检测动作终止条件、判断成功与否，并在失败时诊断原因。二者共同实现智能体与物理世界的闭环交互。由此，工具的组合催生丰富行为，闭环机制使长周期任务在真实环境中得以完成。
原文摘要 · Abstract (English)
The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We present Thea, a harness in which an agentic loop orchestrates robot capabilities, each wrapped as a callable tool. It inherits the core components of coding agents, modified as the physical world requires. The world, however, withholds two abilities that software grants for free: reading the state of the world, and judging the outcome of an action. To bridge these gaps, Thea introduces Scene Graph as Context, a persistent, symbolic representation of the world, and Evaluation as Exit Codes, which detects when an action should terminate, judges whether it succeeded, and on failure diagnoses the cause. Together they close the loop between the agent and the physical world. Rich behaviors then emerge from the composition of tools, and the closed loop carries long-horizon tasks to completion in real environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。