NCP: Verifier-Guided Optimization of Weight-Space Control Policies

원문 초록

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.