构建可观察的循环意识代理，揭示情感耦合如何稳定探索行为。
ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays
- 设计递归持久循环结构，结合感官显著性与情感代理反馈。
- 情感耦合版本在低新奇度场景仍保持稳定探索，扫描事件达31.4次。
- 适合研究意识机制、行为稳定性及情感控制对智能体决策的影响。
基于机器意识的指标方法主张通过跨任务的机制关联证据三角验证，辅以架构可观察性和因果干预。受赫姆弗雷的伊普桑德鲁姆假说启发，我们构建了可观察的ReCoN-Ipsundrum代理，其在ReCoN状态机基础上引入感官显著性$N^s$的递归持久循环，并可选加入反映效价/唤醒的情感代理。在固定参数消融实验（ReCoN、Ipsundrum、Ipsundrum+affect）中，将赫姆弗雷的质感偏好（因感官体验本身而偏好）操作化为受熟悉度控制的风景-平淡路径选择。发现新颖性分离：非情感版本对新颖性敏感（Δ景观进入=0.07），而情感耦合版本即使在景观新颖度较低时（中位数Δ新颖度≈-0.43）仍保持稳定（Δ景观进入=0.01）。在无奖励探索游戏中，情感版本表现出结构化局部调查（扫描事件31.4对比0.9；周期得分7.6）。在疼痛尾部探测中，仅情感版本维持长时间计划性谨慎（尾部持续时间90对比5）。损毁反馈+整合模块后，伊普桑德鲁姆变体的刺激后持续性显著下降（AUC下降27.62、27.9%），而ReCoN不受影响。这些分离现象表明：递归→持久性，情感耦合控制→偏好稳定性、扫描行为与持续谨慎，说明指标类信号可通过工程手段实现，且机制与因果证据应伴随行为标记。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。