arXiv cs.AI· Ahsan Adeel, Talha Bin Riaz·· 2 天前AI 评分22
当现实快过认知：面向可靠智能的新扩展原则
When Reality Outpaces Cognition: A New Scaling Principle for Reliable Intelligence
AI 导读
论文提出以有效连贯认知速度（\(S_C^{\mathrm{eff}}\)）衡量智能系统在观测—现实差距扩大时仍能可靠感知、推理与行动的能力，即系统持续满足预设行为可靠性标准的最高现实速度（\(S_R\)）。
正文 · 原文
Abstract:This paper challenges the understanding capabilities of existing AI paradigms and emerging world models by asking a fundamental question: How quickly can reality change before an intelligent system can no longer reliably perceive, reason, and act? We formulate this as a theory- and model-agnostic challenge in which systems must infer reliable actions for increasingly distant future states across a growing observation--reality gap. We operationalize this challenge through the effective Speed of Coherent Cognition (\(S_C^{\mathrm{eff}}\)), defined as the highest tested Speed of Reality (\(S_R\)) through which a system continuously satisfies a predefined behavioural reliability criterion from baseline. As a proof of concept, reinforcement-learning agents are trained at the baseline \(S_R\) and evaluated, without retraining, as \(S_R\) is increased by up to \(50\times\) while computational resources remain fixed. We compare Transformer and gated-MLP baselines with \(Co^4\), an architecture inspired by cellular mechanisms implicated in conscious processing and awake thought. Across the tested scenarios, \(Co^4\) achieves substantially higher \(S_C^{\mathrm{eff}}\) than the baselines, motivating \(S_C^{\mathrm{eff}}\) as a new benchmark and the scaling of coherent cognition as a principle for reliable AI.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:2610.20764 [cs.AI] |
| (or arXiv:2610.20764v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20764 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ahsan Adeel [view email]
[v1]
Wed, 14 Oct 2026 18:13:18 UTC (12,070 KB)
来源：arXiv cs.AI · arxiv.org