A quantifiable information-processing hierarchy provides a necessary condition for detecting agency

Preprint

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.

Authors: Kagan, BJ; Baccetti, V; Earp, BD; Boyd, JL; Savulescu, J

• Publication status: Published
• Peer review status: Not peer reviewed
• Preprint server: arXiv
• Publication date: 2026-01-07
• DOI: 10.48550/arXiv.2601.03498
• Language: English
• Keywords: information processing; agency; frameworks; ethics; informatics
• Subjects: FOS: Computer and information sciences; Data Analysis, Statistics and Probability (physics.data-an); FOS: Physical sciences; Neurons and Cognition (q-bio.NC); FOS: Biological sciences; Machine Learning (stat.ML); Information Theory (cs.IT)