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

TL;DR

This paper introduces a quantifiable hierarchy of information-processing levels to identify necessary conditions for agency in diverse systems, from neural cultures to machine models.

Contribution

It proposes a bottom-up, measurable framework based on information-processing order to assess agency across different substrates.

Findings

Identifies three classes of information processing: reactive, memory-based, and adaptive.

Demonstrates the hierarchy with neurophysiological and computational examples.

Provides a substrate-independent method to evaluate potential agency.

Abstract

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.