# A Quantifiable Information-Processing Hierarchy Provides a Necessary Condition for Detecting Agency

arXiv: https://arxiv.org/abs/2601.03498 · HTML: https://mlsanity.com/paper/2601.03498/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 88 references that are in the map.
- First posted on arXiv 7 Jan 2026.

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

- [Biological neurons act as generalization filters in reservoir computing](https://mlsanity.com/paper/2210.02913/) (2022)
- [Complex behavior from intrinsic motivation to occupy action-state path space](https://mlsanity.com/paper/2205.10316/) (2022)
- [Agency Is Frame-Dependent](https://mlsanity.com/paper/2502.04403/) (2025)
- [Starting a Synthetic Biological Intelligence Lab from Scratch](https://mlsanity.com/paper/2412.14112/) (2024)
- [How adaptation currents change threshold, gain and variability of neuronal spiking](https://mlsanity.com/paper/1307.5728/) (2013)
- [Impact of adaptation currents on synchronization of coupled exponential integrate-and-fire neurons](https://mlsanity.com/paper/1310.2430/) (2013)

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

- [Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation](https://mlsanity.com/paper/2605.13315/) (2026)

## Abstract (arXiv)

As intelligent systems are developed across diverse substrates - from machine learning models and neuromorphic hardware to in vitro neural cultures - understanding what gives a system agency has become increasingly important. Existing definitions, however, tend to rely on top-down descriptions that are difficult to quantify. We propose a bottom-up framework grounded in a system's information-processing order: the extent to which its transformation of input evolves over time. We identify three orders of information processing. Class I systems are reactive and memoryless, mapping inputs directly to outputs. Class II systems incorporate internal states that provide memory but follow fixed transformation rules. Class III systems are adaptive; their transformation rules themselves change as a function of prior activity. While not sufficient on their own, these dynamics represent necessary informational conditions for genuine agency. This hierarchy offers a measurable, substrate-independent way to identify the informational precursors of agency. We illustrate the framework with neurophysiological and computational examples, including thermostats and receptor-like memristors, and discuss its implications for the ethical and functional evaluation of systems that may exhibit agency.