Interoceptive machine framework: Toward interoception-inspired regulatory architectures in artificial intelligence

TL;DR

This paper introduces the interoceptive machine framework, inspired by biological interoception, to improve self-regulation and adaptability in embodied AI systems through computational principles of internal-state regulation.

Contribution

It proposes a novel integrative framework translating biological interoception principles into AI architectures for enhanced autonomy and adaptive behavior.

Findings

Framework organizes interoceptive functions into three principles: homeostatic, allostatic, enactive.

Embedding internal variables improves decision-making and uncertainty handling.

Framework offers a pathway for self-regulating, adaptive AI agents.

Abstract

This review proposes an integrative framework grounded on interoception and embodied AI-termed the interoceptive machine framework-that translates biologically inspired principles of internal-state regulation into computational architectures for adaptive autonomy. Interoception, conceived as the monitoring, integration, and regulation of internal signals, has proven relevant for understanding adaptive behavior in biological systems. The proposed framework organizes interoceptive contributions into three functional principles: homeostatic, allostatic, and enactive, each associated with distinct computational roles: internal viability regulation, anticipatory uncertainty-based re-evaluation, and active data generation through interaction. These principles are not intended as direct neurophysiological mappings, but as abstractions that inform the design of artificial agents with improved self-regulation and context-sensitive behavior. By embedding internal state variables and regulatory loops within these principles, AI systems can achieve more robust decision-making, calibrated uncertainty handling, and adaptive interaction strategies, particularly in uncertain and dynamic environments. This approach provides a concrete and testable pathway toward agents capable of functionally grounded self-regulation, with direct implications for human-computer interaction and assistive technologies. Ultimately, the interoceptive machine framework offers a unifying perspective on how internal-state regulation can enhance autonomy, adaptivity, and robustness in embodied AI systems