# Message passing-based inference in an autoregressive active inference agent

arXiv: https://arxiv.org/abs/2509.25482 · HTML: https://mlsanity.com/paper/2509.25482/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Expected Free Energy-based Planning as Variational Inference](https://mlsanity.com/paper/2504.14898/) (2025)
- [Realising Synthetic Active Inference Agents, Part II: Variational Message Updates](https://mlsanity.com/paper/2306.02733/) (2023)
- [Active Inference and Epistemic Value in Graphical Models](https://mlsanity.com/paper/2109.00541/) (2021)
- [Information-seeking polynomial NARX model-predictive control through expected free energy minimization](https://mlsanity.com/paper/2312.15046/) (2023)
- [A Unified View of Algorithms for Path Planning Using Probabilistic Inference on Factor Graphs](https://mlsanity.com/paper/2106.10442/) (2021)
- [Online Bayesian system identification in multivariate autoregressive models via message passing](https://mlsanity.com/paper/2506.02710/) (2025)

## Built on by (most cited first, 1 of 1)

- [Expected free energy as an information constraint on the Bethe Lagrangian](https://mlsanity.com/paper/2608.17167/) (2026)

## Abstract (arXiv)

We present the design of an autoregressive active inference agent in the form of message passing on a factor graph. Expected free energy is derived and distributed across a planning graph. The proposed agent is validated on a robot navigation task, demonstrating exploration and exploitation in a continuous-valued observation space with bounded continuous-valued actions. Compared to a classical optimal controller, the agent modulates action based on predictive uncertainty, arriving later but with a better model of the robot's dynamics.