ComBodied Agents：以人為本的代理型人工智慧新範式

摘要

當一位年長者漏服藥物時，軟體智能體可以再發送一次提醒，具身智能體則可以將藥物送來。然而，兩者都無法說明該人是忘記了、感到困惑、出現副作用，還是刻意拒絕服藥，也無法判斷什麼樣的支援才適當。這揭示了智能體人工智慧（Agentic AI）中的結構性缺口：數位智能體主要轉換軟體狀態，具身智能體則轉換物理狀態；兩者都沒有將一個人不斷變化的狀態與能動性作為建模、介入與評估的主要對象。我們引入共體智能體（Combodied Agents），這是一種以人為中心的典範，它隨著時間感知、建模、預測並支援個人的狀態軌跡，並將軟體工具、感測器、穿戴式裝置、機器人及人類服務視為行動管道，而非最終目標。我們將分散在個人助理、健康智能體、AI 伴侶與適應性人機系統中的能力統整為一個閉環：基於事件的多模態感知重建有意義的個人事件；縱貫式、可修正的記憶提供時間脈絡；個人世界模型（Personal World Models）估算在不同決策與介入下未來的個人狀態與結果；而一套可允許的介入策略則在同意、不確定性、安全性、可逆性與使用者控制等條件下，選擇適度的支援。來自個人與環境的回饋會持續更新此閉環。此框架不要求建立詳盡的人類數位孿生，而是採用目的限定、不確定性感知且使用者可修正的表徵。我們以人類狀態標的、關係情境與智能體角色來組織設計空間，並提出以情境為中心的評估、能動性保存指標、基準測試需求、邊緣原生個人模型與治理方向。共體智能體將智能體人工智慧從外部任務完成，轉向持續的人類福祉。

English

After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither explains whether the person forgot, is confused, has side effects, or deliberately refused, nor what support is appropriate. This reveals a structural gap in Agentic AI: Digital Agents primarily transform software states, while Embodied Agents transform physical states; neither makes a person's evolving state and agency the primary object of modeling, intervention, and evaluation. We introduce Combodied Agents, a human-centered paradigm that perceives, models, predicts, and supports individual human-state trajectories over time, using software tools, sensors, wearables, robots, and human services as action channels rather than end goals. We unify fragmented capabilities across personal assistants, health agents, AI companions, and adaptive human--AI systems into a closed loop: event-based multimodal perception reconstructs meaningful personal events; longitudinal, correctable memory provides temporal context; Personal World Models estimate future personal states and outcomes under alternative decisions and interventions; and an admissible intervention policy selects proportionate support under consent, uncertainty, safety, reversibility, and user control. Feedback from the person and environment updates the loop. Rather than requiring an exhaustive Human Digital Twin, the framework uses purpose-bounded, uncertainty-aware, user-correctable representations. We organize the design space by human-state targets, relational contexts, and agent roles, and propose scenario-centered evaluation, agency-preservation metrics, benchmark requirements, edge-native personal models, and governance directions. Combodied Agents shift Agentic AI from external task completion toward sustained human benefit.