具身代理人架構的自動化設計

摘要

具身智能體通常以感知、記憶、規劃與行動模組的手工設計組合方式構建。此模組化特性暴露了廣闊的架構設計空間，但現有系統仍依賴研究者直覺來決定資訊儲存位置、觀測處理方式以及模型調用間的連接關係。智能體架構搜索（AAS）雖能自動化文本領域智能體的此類設計，但尚未透過模擬器部署實驗對具知覺能力的智能體進行系統性評估。本研究探討此跨域遷移。我們提出AgentCanvas——一種類型化圖執行環境，其將具身執行器託管為可編輯的節點-線程程式，並具備模擬器感知執行與回合級日誌功能；以及KDLoop——一種編碼智能體搜索程序，透過提案、評審、實驗與蒸餾的循環運作，並在停滯後觸發反思機制。我們針對四種涵蓋視覺語言導航、具身問答及語言條件操縱的具身執行器，評估了三種AAS變體。由此產生的3x4矩陣表明，架構層級搜索能在具身任務中產生可部署且具方向性的成功率提升，而一個看似高分的候選方案則因存在資訊洩漏而被排除。與此同時，實驗揭示了文本領域AAS中被掩蓋的限制：最佳化訊號可能被部署雜訊掩蓋、搜索可能陷入局部編輯盆地，且即使擁有詳細日誌，回合級信用分配仍僅能部分浮現。這些結果既展現了具身智能體自動化架構搜索的潛力，也凸顯其當前的局限性。

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.