Body-Grounded Perspective Formation and Conative Attunement in Artificial Agents

TL;DR

This paper introduces a minimal architecture enabling artificial agents to form perspectives grounded in their bodies, incorporating interoceptive signals and conative mechanisms to produce stable, body-directed behaviors in a reward-free environment.

Contribution

It extends prior models by integrating interoceptive signals and conative alignment, operationalizing minimal structural conditions for artificial subjectivity.

Findings

Converts bodily tendencies into stable, body-directed behaviors.

Allows bodily perturbations to leave recoverable geometric residues.

Demonstrates operationalization of artificial subjectivity in a minimal setup.

Abstract

This paper proposes a minimal architecture for body-grounded perspective formation in artificial agents. Extending prior work, the model introduces an interoceptive viability signal, a Fisher-style metric over fused exteroceptive-interoceptive states, and a conative alignment mechanism linking bodily tendency to action readiness. In a reward-free gridworld, conation converts learned bodily tendency into stable body-directed behavior, while body-to-perspective routing allows bodily perturbations to leave a recoverable geometric residue in the perspective latent. This study shows how minimal structural conditions for artificial subjectivity can be operationalized in the phenomenological sense, through the embodied organization of how a world is given to an agent.