NCP：基于验证器的权重空间控制策略优化框架
NCP: Verifier-Guided Optimization of Weight-Space Control Policies
AI 导读
arXiv 论文提出神经控制平面（NCP），一个闭环系统，观察语言模型执行、合成候选权重空间干预规则并经验证后维护版本化策略表。在 SmolLM-135M-Instruct 本地实验中，一个投影规则将验证集 token 重复率从 0.4133 降至 0.2191，困惑度变化 -0.0574%；因候选规则均未带来新的正确答案，准入门槛归档全部三个候选并保留原策略。
正文 · 原文
Abstract:We present the Neural Control Plane (NCP), a closed-loop system that observes language-model execution, synthesizes candidate weight-space intervention rules, evaluates them, and maintains a versioned table of admitted policies. NCP separates a pretrained model's inference data plane from the control policy that selects temporary parameter interventions. W-ISA supplies transactional execution and parameter restoration; NCP supplies telemetry, candidate synthesis, admission criteria, priorities, and rule lifetime management. The optimization state consists of active rules and an archive of evaluated candidates, while base-model parameters are restored after each request. In a local SmolLM-135M-Instruct experiment, NCP generated three candidates from development telemetry and evaluated them on separate task examples and a 4,095-target WikiText-2 slice. One projection reduced validation token repetition from 0.4133 to 0.2191, with a perplexity change of -0.0574%. All candidates produced zero newly correct exact answers, so the configured admission gate archived all three and retained the original active policy. Fresh-process repetition and saved-table resumption reproduced the measured outcomes. NCP provides an executable framework for studying recursive self-improvement at the control-policy level through explicit synthesis, verification, and state transitions.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13236 [cs.AI] |
| (or arXiv:2611.13236v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13236 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ekrem Aksoy [view email]
[v1]
Mon, 9 Nov 2026 21:05:21 UTC (12 KB)
来源：arXiv cs.AI · arxiv.org