Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Recurrent Artificial Life Agent

TL;DR

This study demonstrates that in a minimal recurrent agent architecture, prosocial helping behavior emerges when social needs influence self-regulation, especially under affective coupling, without explicit partner-welfare rewards.

Contribution

It introduces a homeostatic sharing mechanism with affect coupling in a self-directed agent, showing prosocial behavior arises from internal regulation rather than external rewards.

Findings

A sharp switch from EAT to PASS at λ* ≈ 0.91 in FoodShareToy.

Affective coupling consistently promotes helping, unlike self-only or partner-observing conditions.

Helping depends on social coupling strength and load conditions, appearing under low load with sufficient coupling.

Abstract

Artificial agents can be made to "help" for many reasons, including explicit social reward, hard-coded prosocial bonuses, or direct access to another agent's internal state. Those possibilities make minimal prosocial behavior hard to interpret. Building on ReCoN-Ipsundrum, an inspectable recurrent controller with affect-coupled regulation, I add an explicit homeostat and a social coupling channel while keeping planning strictly self-directed: the agent scores only its own predicted internal state, and no partner-welfare reward term is introduced. I compare four matched conditions in two toy worlds. In a one-step FoodShareToy, an exact solver finds a sharp switch from EAT to PASS at ${\lambda}* \approx 0.91$ for the default state. In the experimental runs, the self-only and partner-observing conditions never help, whereas the affectively coupled conditions always do. In a multi-step SocialCorridorWorld, the same dissociation reappears: coupling flips help rate and partner recovery from 0 to 1 and cuts rescue latency from 18 to 9 steps, while raising mutual viability from 0.15 to 0.33. Sham lesions preserve helping, but coupling-off and shuffled-partner lesions abolish it in both tasks. A coupling sweep shows a load-dependent feasibility boundary: under low load, helping appears for ${\lambda} \geq 0.25$, whereas under medium and high loads no tested value rescues the partner within horizon. The result is a narrow claim for artificial life: in this minimal architecture, helping appears when another's need is routed into self-regulation.