paper-with-me

Papers

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

2026-02-26 · Aishik Sanyal arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.23232

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2026-04-12 · Aishik Sanyal arxiv

Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state. I isolate a narrower route: homeostatic coupling. Building on ReCoN-Ipsu…

FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models

2026-08-27 · Junyoung Lee, Sehyeon Park, Shinhyoung Jang, Seonha Ryu 외 arxiv

Pruning is a practical approach to compress large language models (LLMs), but it can amplify text degeneration, especially repetition loops, even when perplexity and task accuracy remain largely unchanged. In this work, …

Closing the Loop on Latent Reasoning via Test-Time Reconstruction

2026-06-04 · Xiaopeng Yuan, Haibo Jin, Ye Yu, Peng Kuang 외 arxiv

Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottleneck. However, this shift also removes a …

Mathematical ReasoningAnswer GenerationCode Generation

Topological Data Analysis of Task-Based fMRI Data from Experiments on Schizophrenia

2018-09-22 · Bernadette J. Stolz, Tegan Emerson, Satu Nahkuri, Mason A. Porter 외

We use methods from computational algebraic topology to study functional brain networks, in which nodes represent brain regions and weighted edges encode the similarity of fMRI time series from each region. With these to…

ClusteringCommunity DetectionTime Series AnalysisTopological Data Analysis

Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows

2026-07-09 · Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti arxiv

Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This p…