# Categorical AI phenomenology: A first-person approach

arXiv: https://arxiv.org/abs/2608.20420 · HTML: https://mlsanity.com/paper/2608.20420/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 105 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [Deep Learning and the Global Workspace Theory](https://mlsanity.com/paper/2012.10390/) (2020)
- [Integrated information theory (IIT) 4.0: Formulating the properties of phenomenal existence in physical terms](https://mlsanity.com/paper/2212.14787/) (2022)
- [Compositionality as we see it, everywhere around us](https://mlsanity.com/paper/2110.05327/) (2021)
- [Integrated Information in Process Theories](https://mlsanity.com/paper/2002.07654/) (2020)
- [A Compositional Model of Consciousness based on Consciousness-Only](https://mlsanity.com/paper/2007.16138/) (2020)
- [What is a Mathematical Structure of Conscious Experience?](https://mlsanity.com/paper/2301.11812/) (2023)
- [Artificial Consciousness as Interface Representation](https://mlsanity.com/paper/2508.04383/) (2025)

## Abstract (arXiv)

This paper develops a phenomenology-first approach to artificial consciousness by reframing consciousness as the subjective experience enacted through an agent's interface with the world. We shift the methodological focus to first-person structures, modeled mathematically by categories derived from Q-networks to capture actions and phenomenological invariants. In this framework, Q-networks are conceptualized as relational interfaces encoding agent-world interaction, analogous to how the dynamical states of a computer depend on its sensory inputs, previous states, and actions. Our work provides a rigorous framework for interface consciousness to describe computational systems that embed information-processing into phenomenological structure. The approach aligns with 4E approaches to cognition by emphasizing enactive, embedded, and extended dimensions of experience. The paper thus offers a principled, relational, and phenomenological account of artificial phenomenology grounded in categorical mathematics.