# The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness

arXiv: https://arxiv.org/abs/2506.13825 · HTML: https://mlsanity.com/paper/2506.13825/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 4 of 4)

- [When the map is better than the territory](https://mlsanity.com/paper/1612.09592/) (2016)
- [Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data](https://mlsanity.com/paper/2004.08220/) (2020)
- [Towards an extended taxonomy of information dynamics via Integrated Information Decomposition](https://mlsanity.com/paper/2109.13186/) (2021)
- [Towards a (meta-)mathematical theory of consciousness: universal (mapping) properties of experience](https://mlsanity.com/paper/2412.12179/) (2024)

## Abstract (arXiv)

Research on artificial consciousness lacks the equivalent of the perceptron: a small, trainable module that can be copied, benchmarked, and iteratively improved. We introduce the Reflexive Integrated Information Unit (RIIU), a recurrent cell that augments its hidden state h with two additional vectors: (i) a meta-state μ that records the cell's own causal footprint, and (ii) a broadcast buffer B that exposes that footprint to the rest of the network. A sliding-window covariance and a differentiable Auto-Phi surrogate let each RIIU maximize local information integration online. We prove that RIIUs (1) are end-to-end differentiable, (2) compose additively, and (3) perform Phi-monotone plasticity under gradient ascent. In an eight-way Grid-world, a four-layer RIIU agent restores >90% reward within 13 steps after actuator failure, twice as fast as a parameter-matched GRU, while maintaining a non-zero Auto-Phi signal. By shrinking "consciousness-like" computation down to unit scale, RIIUs turn a philosophical debate into an empirical mathematical problem.