ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays

TL;DR

This paper introduces ReCoN-Ipsundrum, an inspectable recurrent agent with affect coupling, demonstrating how mechanistic indicators can reveal consciousness-like features through causal and architectural analysis.

Contribution

It presents a novel agent architecture that integrates recurrent persistence loops with affect proxies, operationalizing mechanism-linked consciousness indicators with experimental validation.

Findings

Affect coupling stabilizes persistence even with less novelty.

Affect variant shows structured exploration and prolonged caution.

Lesioning feedback reduces post-stimulus persistence significantly.

Abstract

Indicator-based approaches to machine consciousness recommend mechanism-linked evidence triangulated across tasks, supported by architectural inspection and causal intervention. Inspired by Humphrey's ipsundrum hypothesis, we implement ReCoN-Ipsundrum, an inspectable agent that extends a ReCoN state machine with a recurrent persistence loop over sensory salience $N^s$ and an optional affect proxy reporting valence/arousal. Across fixed-parameter ablations (ReCoN, Ipsundrum, Ipsundrum+affect), we operationalize Humphrey's qualiaphilia (preference for sensory experience for its own sake) as a familiarity-controlled scenic-over-dull route choice. We find a novelty dissociation: non-affect variants are novelty-sensitive ($\Delta$scenic-entry = 0.07). Affect coupling is stable ($\Delta$scenic-entry = 0.01) even when scenic is less novel (median {$\Delta$novelty $\approx$ -0.43). In reward-free exploratory play, the affect variant shows structured local investigation (scan events 31.4 vs. 0.9; cycle score 7.6). In a pain-tail probe, only the affect variant sustains prolonged planned caution (tail duration 90 vs. 5). Lesioning feedback+integration selectively reduces post-stimulus persistence in ipsundrum variants (AUC drop 27.62, 27.9%) while leaving ReCoN unchanged. These dissociations link recurrence $\rightarrow$ persistence and affect-coupled control $\rightarrow$ preference stability, scanning, and lingering caution, illustrating how indicator-like signatures can be engineered and why mechanistic and causal evidence should accompany behavioral markers.