ETA：一种用于具身任务的新型智能体范式
ETA: A New Agentic Paradigm for Embodied Tasks
浏览论文内容
中文总结 AI 辅助
针对当前具身系统泛化依赖训练数据、长时执行难控的问题，提出新型具身任务智能体范式ETA，发布开源实现OpenETA，为Codex提供轻量级插件以支持具身任务处理。
中文摘要 AI 辅助
机器人何时能迎来属于它们的ChatGPT时刻？这一突破需要一款通用机器人，该机器人能够在陌生环境中处理陌生任务、在长时间交互中保持可控性并从经验中学习。当前的具身系统大多遵循从观测到动作的端到端路径。尽管取得了快速进展，但它们仍远未达到这一目标：其泛化能力高度依赖机器人训练数据的覆盖范围，而长时间任务执行仍难以控制和检查。为实现这一目标，我们提出Embodied Task Agent（ETA，具身任务智能体），这是一种将数字智能体扩展到物理世界的新型范式，并发布其开源实现OpenETA。ETA围绕三个核心组件构建：每次选择一个工具调用的规划器（Planner）、控制执行的接口（Interface）、返回结果和新观测值的世界（World）。该循环使智能体能够验证结果、调整其规划，并将成功和失败的交互转化为可复用的经验。OpenETA提供可替换的规划器、可组合的工具（Tools）和技能（Skills）、可审计的内存、可回放的轨迹，以及适用于仿真和真实机器人的通用接口。对于Codex，OpenETA可作为轻量级插件运行，仅暴露观测（observe）、标记点（mark_point）和移动到（move_to）功能。
英文摘要
When will robots have their ChatGPT moment? Such a breakthrough requires a general-purpose robot that can handle unfamiliar tasks in unfamiliar environments, remain controllable over long interactions, and learn from experience. Today's embodied systems largely follow an end-to-end observation-to-action path. Despite rapid progress, they remain far from this goal: their generalization depends heavily on the coverage of robot training data, while long task execution remains difficult to control and inspect. To realize this goal, we introduce the Embodied Task Agent (ETA), a new paradigm for extending digital agents into the physical world, and release OpenETA as its open-source implementation. ETA centers the robot around a Planner that chooses one Tool call at a time, an Interface that controls execution, and a World that returns the result and a fresh observation. This loop allows the agent to verify outcomes, adapt its plan, and turn successful and failed interactions into reusable experience. OpenETA provides replaceable Planners, composable Tools and Skills, auditable memory, replayable trajectories, and common interfaces for simulation and real robots. For Codex, OpenETA can operate as a lightweight plugin that exposes only observe, mark_point, and move_to.
