arXiv cs.AI· Byung Gyu Chae·· 12 小时前AI 评分31
超越片段式 AI：Cognitive Field Network 如何实现生物启发的持久认知
Beyond Episodic AI: Cognitive Field Networks for Biologically Inspired Persistent Cognition
AI 导读
研究者提出 Cognitive Field Network（CFN），一种带隐藏场重入的循环 Transformer 架构，让完整 token 级隐藏场重新进入下一计算周期，而非依赖显式记忆操作。
正文 · 原文
Abstract:Cognitive Field Theory describes cognition as memory-dressed collective dynamics, in which slow relaxation modes support a persistent cognitive field. By connecting non-Markovian memory dynamics to discrete recurrent state evolution through an extended state, we develop a Cognitive Field Network (CFN), a recurrent Transformer architecture with hidden-field re-entry, \( \Phi_{n+1} = F_\theta(X_{n+1},\Phi_n) \). Rather than prescribing an explicit memory operation, the CFN allows the full token-resolved hidden field to re-enter the next computational cycle. We find that learning organizes this pathway into a functional channel for persistent, content-dependent internal states, with temporal persistence systematically controlled by the recurrent training horizon. The learned dynamics generalize beyond this horizon: semantic continuation sustains the recurrent state without explicit answer replay, whereas unsupported states exhibit finite passive relaxation. Periodic re-exposure to relevant input renews the surviving field, producing an approximately stationary nonzero regime over extended recurrent trajectories. Unrelated-input and recurrence-off controls fail to reproduce this behavior, while near-paraphrased input produces weaker renewal, revealing the dependence of persistence on both field re-entry and input relevance. These findings connect memory-dressed field formation, input-driven reorganization, and recurrent state continuity within a unified dynamical framework. The CFN thus provides an experimentally controllable platform for studying persistent, history-dependent cognition without a separately prescribed memory system.
| Comments: | 42 pages, 13 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.16752 [cs.AI] |
| (or arXiv:2609.16752v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.16752 arXiv-issued DOI via DataCite |
Submission history
From: Byung Gyu Chae [view email]
[v1]
Tue, 15 Sep 2026 07:29:04 UTC (2,921 KB)
[v2]
Sun, 20 Sep 2026 22:24:52 UTC (3,023 KB)
[v3]
Tue, 20 Oct 2026 09:29:39 UTC (3,283 KB)
来源：arXiv cs.AI · arxiv.org