发表机构
Université de Montréal; Mila – Quebec Artificial Intelligence Institute; Institute of Advanced Intelligence and Computing (IAIC), A*STAR; Nanjing Medical University; Nanjing University; Renmin University of China; University of Cambridge; University of Oxford; Tsinghua University; National University of Singapore; The Hong Kong University of Science and Technology; The Hong Kong Polytechnic University; Southern University of Science and Technology; Southeast University; University of Glasgow; Nanyang Technological University（蒙特利尔大学; 米拉-魁北克人工智能研究所; 新加坡科技研究局高级智能与计算研究所; 南京医科大学; 南京大学; 中国人民大学; 剑桥大学; 牛津大学; 清华大学; 新加坡国立大学; 香港科技大学; 香港理工大学; 南方科技大学; 东南大学; 格拉斯哥大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出以人为中心的 Combodied Agents 新范式，整合多类智能体能力形成闭环，聚焦人类状态轨迹建模，推动智能体 AI 从任务完成转向人类持续福祉。
AI 中文摘要
当一位老年人错过一剂药物服用后，软件智能体可发送另一条提醒，而具身智能体可将药物送到其面前。然而，两者均未解释该老人是忘记了、感到困惑、出现副作用，还是故意拒绝，也未说明何种支持是合适的。这揭示了智能体人工智能领域存在的结构性缺口：数字智能体主要转换软件状态，而具身智能体转换物理状态；两者均未将人的动态状态与能动性作为建模、干预和评估的主要对象。我们提出 Combodied Agents（具身融合智能体），这是一种以人为中心的范式，它利用软件工具、传感器、可穿戴设备、机器人和人类服务作为行动渠道而非最终目标，来感知、建模、预测并支持个体随时间变化的人类状态轨迹。我们将个人助手、健康智能体、AI伴侣和自适应人机系统的零散能力统一为一个闭环：基于事件的多模态感知重构有意义的个人事件；可修正的纵向记忆提供时间上下文；Personal World Models（个人世界模型）在不同决策和干预措施下预测未来的个人状态与结果；可接受的干预策略在用户同意、不确定性、安全性、可逆转性及用户控制的前提下选择相称的支持。来自人和环境的反馈会更新该闭环。该框架不要求构建详尽的 Human Digital Twin（数字孪生人类），而是采用目标受限、感知不确定性、可由用户修正的表示。我们按人类状态目标、关系情境和智能体角色组织设计空间，并提出以场景为中心的评估、能动性保留指标、基准要求、边缘原生个人模型及治理方向。Combodied Agents 将智能体人工智能从外部任务完成转向持续的人类福祉提升。
英文摘要
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.
Comments38 pages, 6 figures, 10 tables
