# The Bayesian Reflex: A Predictive Coding Engine for Artificial Intelligence

arXiv: https://arxiv.org/abs/2608.00492 · HTML: https://mlsanity.com/paper/2608.00492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 1 Aug 2026.

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

- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [On Geometric Ergodicity of Additive and Multiplicative Transformation Based Markov Chain Monte Carlo in High Dimensions](https://mlsanity.com/paper/1312.0915/) (2013)
- [How Ominous is the Premonition of Future Global Warming?](https://mlsanity.com/paper/2008.11175/) (2020)
- [Function Optimization with Posterior Gaussian Derivative Process](https://mlsanity.com/paper/2010.13591/) (2020)
- [IID Sampling from Intractable Distributions](https://mlsanity.com/paper/2107.05956/) (2021)
- [The Bayesian Reflex: Online Learning as the Autonomic Nervous System of Modern and Future AI](https://mlsanity.com/paper/2605.02825/) (2026)

## Abstract (arXiv)

Predictive coding offers a powerful theory of cortical computation, but corresponding scalable algorithmic implementations for artificial intelligence have remained elusive. This paper introduces the Bayesian reflex, a computational framework that directly instantiates predictive coding through three pillars: belief maintenance via hierarchical generative models, sequential Bayesian updating via prediction-error minimization, and uncertainty-driven action via active inference. We show that recent breakthroughs---ellipsoidal decomposition for exact i.i.d. sampling, recursive Gaussian processes for deep hierarchical inference, and derivative-aware Bayesian optimization---provide the missing algorithmic ingredients. The resulting framework enables mathematically principled, scalable, and brain-inspired continual learning, perception, and decision-making. We illustrate its versatility through applications ranging from climate model evaluation to prime number discovery, offering a blueprint for truly adaptive artificial intelligence.