# 从被动镜像到主动智能体：面向网络物理AI的Holonic Digital Twins

> 原文链接：https://robotics.hellobike.com/papers/2026-08-06-2608-06227
> 频道：papers | 更新日期：2026-08-06 | 标签：arxiv, cs.RO
> 核心摘要：针对物理系统中AI难以共享时空上下文与长程规划的问题，提出HDT-Nets框架用于实时物理AI推理。

# 从被动镜像到主动智能体：面向网络物理AI的Holonic Digital Twins

::: v-pre
> 原文链接：[From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks](https://arxiv.org/abs/2608.06227)（arXiv 2608.06227 · 发布日期：2026-08-06）

**From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks**

针对物理系统中AI难以共享时空上下文与长程规划的问题，提出HDT-Nets框架用于实时物理AI推理。

## 核心要点

- 现有AI嵌入机器人和车辆等物理系统时，难以维持可靠世界模型并泛化到未见场景。
- HDT-Nets让holonic agents主动推理环境，并在本地自治推理与邻近HDT协作间形成集体智能。
- 框架用因果Markov blankets界定协同范围，以主动推理统一感知、行动和学习。
- 摘要未提及实验结果或开源，仅阐述类别论与整合信息理论等框架组成。

## 英文摘要 (Abstract)

Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when embedded into physical systems, such as robots and vehicles operating under real-world physical laws. This stems from their inability to maintain reliable world models for long-horizon planning under uncertainty and generalize to unseen scenarios. In this context, wireless networks, through pervasive sensing and communication, can orchestrate physical intelligence. However, current architectures optimize throughput, latency, and reliability and cannot support real-time physical AI coordination, requiring agents to maintain shared spatiotemporal context. To address these challenges, a network of holonic digital twins (HDT-Nets) framework is proposed to deliver real-time physical AI inference through holonic agents that actively reason about their environment rather than passively mirror physical assets. Each HDT is realized as a hierarchical structure spanning the physical agent and network edge, reasoning autonomously at the local level while cooperating with neighboring HDTs to form collectively intelligent units. In HDT-Net, causal Markov blankets spanning sensing, communication, and control determine which agents must coordinate and enable counterfactual reasoning over multi-domain interventions. Active inference within these boundaries unifies perception, action, and learning by minimizing expected free energy while deciding which beliefs to transmit based on their cognitive value to the receiver. Category theory ensures that transmitted beliefs preserve semantic structure across heterogeneous agents with incompatible representations. Finally, integrated information theory quantifies when collective intelligence exceeds independent operation and how network intelligence evolves through coordinated learning and information exchange.

作者：Christo Kurisummoottil Thomas, Omar Hashash, Walid Saad
:::

## 原始参考来源 (Sources)

- [arXiv 2608.06227：From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks](https://arxiv.org/abs/2608.06227)