Jul 2026
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
Multi-Head Latent Control is introduced, a lightweight layer that reads hidden-state trajectories from a frozen LLM or VLM to produce deployment-time control signals, enabling early handoff from partial generations and more accurate intervention decisions in multi-model systems.
Amirhosein Ghasemabadi, Rui-Chen Chen, Bahador Rashidi et al.
· arXiv.org · 0 citations