ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays
This work is an incremental step towards engineering and understanding mechanism-linked indicators of consciousness in AI agents, primarily for researchers in AI and cognitive science.
The paper introduces ReCoN-Ipsundrum, an agent extending a ReCoN state machine with a recurrent persistence loop and an optional affect proxy. It demonstrates that affect coupling stabilizes preference for sensory experience (scenic-entry $\Delta$ = 0.01 vs. 0.07 for non-affect variants) even when novelty is lower, and leads to structured local investigation (31.4 scan events vs. 0.9) and sustained caution (90 vs. 5 tail duration) in reward-free exploration.
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 ($Δ$scenic-entry = 0.07). Affect coupling is stable ($Δ$scenic-entry = 0.01) even when scenic is less novel (median {$Δ$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.