迈向具身智能体的管控
Towards the Harness of Embodied Agents
浏览论文内容
中文总结 AI 辅助
本文提出名为Thea的具身智能体管控系统，通过场景图和退出码评估弥合物理世界与智能体的差距，实现长程任务完成。
中文摘要 AI 辅助
编码智能体的成功已确立了管控这一范式：智能体的成效不仅取决于模型，还取决于其周围的基础设施。本文探究该范式是否适用于物理世界中的具身智能体。我们提出Thea，一种管控系统，其中智能体循环将机器人能力编排为可调用工具，它继承了编码智能体的核心组件，并根据物理世界的需求进行了修改。然而，物理世界缺少软件免费提供的两种能力：读取世界状态和判断动作结果。为弥合这些差距，Thea引入了作为上下文的场景图（Scene Graph as Context），这是一种持久的世界符号表示；以及作为退出码的评估（Evaluation as Exit Codes），它可检测动作何时应终止、判断是否成功，并在失败时诊断原因。两者共同闭合了智能体与物理世界之间的循环，工具的组合可产生丰富行为，该闭环能在真实环境中完成长程任务。
英文摘要
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.
