ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
- Published
- Source
- arXiv
- Paper number
- 879
- Field
- AI / General
- arXiv ID
- 2608.10915
Key points
- It proposes the Combodied Agents paradigm, which goes beyond the digital-agent and robot-agent split by treating the human state trajectory itself as the primary modeling target.
- It designs an integrated closed loop of multimodal perception, long-term memory, personal world models, adaptive intervention policies, and feedback.
- It clearly distinguishes this from human digital twins: it uses uncertainty-aware representations tailored to the task and does not require full replication.
- It organizes the full design space, including edge-native personal models, scenario-centered evaluation, autonomy-preserving metrics, and governance directions.
- It argues that success should be defined not by replacement of human work, but by improvement of human capability and judgment.
Paper links
External research summaries. These are not HDATF publications or measured product results.