# Active Inference for Physical AI Agents -- An Engineering Perspective

arXiv: https://arxiv.org/abs/2603.20927 · HTML: https://mlsanity.com/paper/2603.20927/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [A free energy principle for a particular physics](https://mlsanity.com/paper/1906.10184/) (2019)
- [The free energy principle made simpler but not too simple](https://mlsanity.com/paper/2201.06387/) (2022)
- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [Path integrals, particular kinds, and strange things](https://mlsanity.com/paper/2210.12761/) (2022)
- [Active Inference as a Model of Agency](https://mlsanity.com/paper/2401.12917/) (2024)
- [Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science](https://mlsanity.com/paper/2603.15381/) (2026)
- [Expected Free Energy-based Planning as Variational Inference](https://mlsanity.com/paper/2504.14898/) (2025)
- [Supervised structure learning](https://mlsanity.com/paper/2311.10300/) (2023)
- [Markov Blankets in the Brain](https://mlsanity.com/paper/2006.02741/) (2020)
- [Dynamic Markov Blanket Detection for Macroscopic Physics Discovery](https://mlsanity.com/paper/2502.21217/) (2025)
- [A Message Passing Realization of Expected Free Energy Minimization](https://mlsanity.com/paper/2508.02197/) (2025)
- [Parcels and particles: Markov blankets in the brain](https://mlsanity.com/paper/2007.09704/) (2020)
- [Entropy, Information, and the Updating of Probabilities](https://mlsanity.com/paper/2107.04529/) (2021)
- [Active inference and artificial reasoning](https://mlsanity.com/paper/2512.21129/) (2025)

## Built on by (most cited first, 2 of 2)

- [Design, Cups, and Blankets. A Free-Energy-Principle-Based Approach to Product Design](https://mlsanity.com/paper/2604.22902/) (2026)
- [From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks](https://mlsanity.com/paper/2608.06227/) (2026)

## Abstract (arXiv)

Physical AI agents, such as robots and other embodied systems operating under tight and fluctuating resource constraints, remain far less capable than biological agents in open-ended real-world environments. This paper argues that Active Inference (AIF), grounded in the Free Energy Principle, offers a principled foundation for closing that gap. We develop this argument from first principles, following a chain from probability theory through Bayesian machine learning and variational inference to active inference and reactive message passing. From the FEP perspective, systems that maintain their structural and functional integrity over time can, under suitable assumptions, be described as minimizing variational free energy (VFE), and AIF operationalizes this by unifying perception, learning, planning, and control within a single computational objective. We show that VFE minimization is naturally realized by reactive message passing on factor graphs, where inference emerges from local, parallel computations. This realization is well matched to the constraints of physical operation, including hard deadlines, asynchronous data, fluctuating power budgets, and changing environments. Because reactive message passing is event-driven, interruptible, and locally adaptable, performance degrades gracefully under reduced resources while model structure can adjust online. We further show that, under suitable coupling and coarse-graining conditions, coupled AIF agents can be described as higher-level AIF agents, yielding a homogeneous architecture based on the same message-passing primitive across scales. Our contribution is not empirical benchmarking, but a clear theoretical and architectural case for the engineering community.