SOPHIA

SOPHIA: Activation steering to break LLMs out of reasoning self-loops at inference time

Researchers introduce SOPHIA (Steering Of reasoning Processes via Hidden-state Intervention and Activations), a method for fine-grained control over LLM reasoning traces via inference-time activation steering. The approach models each reasoning trace as a sequence of latent states, builds a bank of steering vectors indexed by state-pair transitions, and uses a controller to detect and intervene on self-loops — failure modes where models exhaust their token budget without progress. Experiments show SOPHIA reliably breaks self-loops and improves both end-task accuracy and token efficiency, with steering vectors that generalize across state pairs.