ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Qianggang Ding, Xingyao Wang, Rui Feng, Zhibin Wang, Feixiang Wang, Kelong Mao, Hao Sun, Zhiyao Luo, Jiankai Tang, Lei Li, Jiadong Guo, Minheng Ni, Weicong Lin, Chenxi Yang, Hongxiang Gao, Zhenghua Chen, Yang Bai, Min Wu, Jun Cheng, Huazhu Fu, Dacheng Tao, Bang Liu
• Venue: arXiv: cs.AI
• Published: 2026-08-11
• Collected: 2026-08-12
• URL: http://arxiv.org/abs/2608.10915v1
• PDF: https://arxiv.org/pdf/2608.10915v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The text discusses a new paradigm called ComBodied Agents, which aims to bridge the gap between digital and embodied artificial intelligence by focusing on modeling, predicting, and supporting individual humans over time. The goal is to move away from completing external tasks and towards promoting sustained human benefits.

What the Document Says

• The text introduces ComBodied Agents, a new paradigm for Agentic AI that focuses on perceiving, modeling, predicting, and supporting individual humans over time.
• ComBodied Agents use software tools, sensors, wearables, robots, and human services as action channels rather than end goals.
• The framework consists of event-based multimodal perception, longitudinal, correctable memory, Personal World Models, and an admissible intervention policy.
• Personal World Models estimate future personal states and outcomes under alternative decisions and interventions.
• An admissible intervention policy selects proportionate support under consent, uncertainty, safety, reversibility, and user control.
• Feedback from the person and environment updates the loop.
• The framework does not require an exhaustive Human Digital Twin.
• The design space is organized by human-state targets, relational contexts, and agent roles.
• Scenario-centered evaluation, agency-preservation metrics, benchmark requirements, edge-native personal models, and governance directions are proposed.

Key Concepts Mentioned

• ComBodied Agents
• Agentic AI
• Software tools
• Sensors
• Wearables
• Robots
• Human services
• Personal assistants
• Health agents
• AI companions
• Adaptive human-AI systems
• Event-based multimodal perception
• Longitudinal, correctable memory
• Personal World Models
• Admissible intervention policy
• Consent
• Uncertainty
• Safety
• Reversibility
• User control
• Feedback
• Human Digital Twin
• Design space
• Scenario-centered evaluation
• Agency-preservation metrics
• Benchmark requirements
• Edge-native personal models
• Governance directions

Claims Made by the Document

• ComBodied Agents address a structural gap in Agentic AI by focusing on individual humans' evolving state and agency.

Evidence Used

• The text states that ComBodied Agents perceive, model, predict, and support individual human-state trajectories over time.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.