具身智能体架构的自动化设计

摘要

具身智能体通常被构建为感知、记忆、规划与行动模块的手工设计组合。这种模块化设计暴露了庞大的架构设计空间，但当前系统仍依赖研究者的直觉来选择信息存储位置、观测处理方式以及模型调用的连接方式。智能体架构搜索（AAS）实现了文本领域智能体的此类自动化设计，但尚未通过模拟器推演在感知型具身智能体上进行系统评估。本研究将探讨这一迁移问题。我们提出AgentCanvas——一种类型图运行时环境，将具身执行器封装为可编辑的节点-连线程序，具备模拟器感知执行能力与回合级日志记录功能；同时提出KDLoop——一种编码智能体搜索流程，通过提案、批评、实验与蒸馏的循环迭代，并在搜索停滞时触发反思机制。我们评估了三种AAS变体在四种具身执行器上的表现，涵盖视觉语言导航、具身问答及语言条件操控任务。得到的3×4矩阵显示：架构级搜索能够为具身任务带来可部署的方向性成功率提升，同时一个表面高分候选方案因存在信息泄露而被否决。然而，实验也暴露了文本领域AAS中被掩盖的约束：优化信号可能被推演噪声掩盖，搜索可能陷入局部编辑盆地，且即便获得详细日志，回合级信用分配也只能部分实现。这些结果刻画了面向具身智能体的自动化架构搜索的前景与当前局限。

English

Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been systematically evaluated on perceptual embodied agents through simulator rollouts. We study this transfer. We introduce AgentCanvas, a typed-graph runtime that hosts embodied executors as editable node-and-wire programs with simulator-aware execution and episode-level logs, and KDLoop, a coding-agent search procedure that cycles through proposal, critique, experiment, and distillation, with triggered reflection after stalls. We evaluate three AAS variants across four embodied executors spanning vision-language navigation, embodied question answering, and language-conditioned manipulation. The resulting 3x4 matrix shows that architecture-level search can produce deployable and directional success-rate gains on embodied tasks, while one apparent high-scoring candidate is rejected as leak-bearing. At the same time, the experiments expose constraints that are muted in text-domain AAS: optimization signals can be masked by rollout noise, search can become trapped in local edit basins, and episode-level credit assignment only partially emerges even when detailed logs are available. These results characterize both the promise and the current limits of automated architecture search for embodied agents.