Ze-Yuan Wang

LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents

This work introduces Global Executive Control (GEC) v0.2, an uncertainty-aware governance architecture that separates action generation from project-level control and mechanistic simulations support explicit governance of scope, evidence, resource use, and stopping, while live-model validation remains necessary.