arXiv cs.AI· Haibin Tong, Luming Guo, Nana Cui, Jiang Yu·· 12 小时前AI 评分31
数字生命的时间组织层：时分复用如何调度持续智能体的忙闲节律
Time-Division Multiplexing: The Operational Rhythm and Temporal Organization Layer of Digital Life
AI 导读
研究者提出一种带相位标记微纪元的时间组织层，用可观测占空比、独立的内容与资源控制及三层嵌套时钟，把持续智能体的在线（忙）与离线（闲）通道统一为同一过程的两个相位。在增益/噪声模型中最佳增益比为 1.55，解耦调度在构造的紧急/高负载子集上成功率达 26.6%，而对照为 11.1%。基于冻结骨干的 Qwen3-8B 原型仅用于检验编排，其结果不构成任务基准证据。
正文 · 原文
Abstract:Continual agents must handle urgent interaction while retaining alternatives, replaying errors, and committing safe long-term changes. A previous digital-life framework distinguishes online (busy) and offline (idle) channels, but leaves open whether these are separate programs or phases of a common process and how their operations should be ordered. Motivated by recent observations of rapidly alternating perceptual representations in primate cortex, we develop a temporal organization layer with phase-tagged micro-epochs, an observable duty cycle, independent content and resource controls, and three nested clocks separating candidate exploration from durable commitment. We give a projected duty-cycle update, state its deterministic descent guarantee and the additional noise term required for a stochastic guarantee, and specify coupled busy/idle execution contracts. Five synthetic experiments (64 seeds each) examine descent and noise, objective misalignment, gain asymmetry, resource coupling, and dropped replay logs. In the gain/noise model the best tested gain ratio is 1.55; decoupled scheduling yields 26.6% versus 11.1% success on a constructed urgent/high-load subset. A frozen-backbone Qwen3-8B prototype further checks orchestration, but its proxy outcomes are not task-benchmark evidence. The results establish a testable scheduling design and identify its conditions of validity, not machine consciousness or general-purpose agent superiority.
| Comments: | 30 pages, 6 figures |
| Subjects: | Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2611.06603 [cs.AI] |
| (or arXiv:2611.06603v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06603 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiang Yu [view email]
[v1]
Wed, 4 Nov 2026 14:54:53 UTC (957 KB)
来源：arXiv cs.AI · arxiv.org