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

arXiv: https://arxiv.org/abs/2608.06227 · HTML: https://mlsanity.com/paper/2608.06227/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Large Wireless Model (LWM): A Foundation Model for Wireless Channels](https://mlsanity.com/paper/2411.08872/) (2024)
- [Digital-Twin-Enabled 6G: Vision, Architectural Trends, and Future Directions](https://mlsanity.com/paper/2102.12169/) (2021)
- [Artificial General Intelligence (AGI)-Native Wireless Systems: A Journey Beyond 6G](https://mlsanity.com/paper/2405.02336/) (2024)
- [Learning Radio Environments by Differentiable Ray Tracing](https://mlsanity.com/paper/2311.18558/) (2023)
- [Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn from a Digital Twin](https://mlsanity.com/paper/1907.01523/) (2019)
- [Causal Reasoning: Charting a Revolutionary Course for Next-Generation AI-Native Wireless Networks](https://mlsanity.com/paper/2309.13223/) (2023)
- [Deep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network](https://mlsanity.com/paper/2201.04712/) (2022)
- [Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach](https://mlsanity.com/paper/2304.12502/) (2023)
- [DMWM: Dual-Mind World Model with Long-Term Imagination](https://mlsanity.com/paper/2502.07591/) (2025)
- [Dynamic Markov Blanket Detection for Macroscopic Physics Discovery](https://mlsanity.com/paper/2502.21217/) (2025)
- [From Simulators to Digital Twins for Enabling Emerging Cellular Networks: A Tutorial and Survey](https://mlsanity.com/paper/2411.08907/) (2024)
- [MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind](https://mlsanity.com/paper/2603.00808/) (2026)
- [Time, Simultaneity, and Causality in Wireless Networks with Sensing and Communications](https://mlsanity.com/paper/2401.08258/) (2024)
- [LLM-Integrated Digital Twins for Hierarchical Resource Allocation in 6G Networks](https://mlsanity.com/paper/2506.18293/) (2025)
- [Active Inference for Physical AI Agents -- An Engineering Perspective](https://mlsanity.com/paper/2603.20927/) (2026)
- [Digital-Twin-Aided Dynamic Spectrum Sharing and Resource Management in Integrated Satellite-Terrestrial Networks](https://mlsanity.com/paper/2602.09191/) (2026)
- [Active Inference as the Test-Time Scaling Law for Physical AI Agents](https://mlsanity.com/paper/2606.22813/) (2026)

## Abstract (arXiv)

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.