Abstract
Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt-based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in the reasoning traces from Large Language Models.
Building on this, we statistically characterize these states and show that failure trajectories get stuck in self-loops, exhausting the token budget without progress toward the final answer.
To intervene on these failures, we propose SOPHIA: Steering Of reasoning Processes via Hidden-state Intervention and Activations. We treat each reasoning trace as a sequence of latent states rather than unstructured texts and investigate whether inference time interventions can provide fine-grained control over the self-looping reasoning process.
We classify every prefix to a latent state, record step-level transitions, and use them to construct a bank of steering vectors indexed by state pairs. At inference time, a controller infers the current state and, given a target state, retrieves the corresponding vector and can also detect self-loops online from the transition structure to prevent the model from sinking into a reasoning black hole.
Through extensive experiments, our method reliably intervenes on self-loop failures, with steering vectors that generalize to different state pairs. End task accuracy and token efficiency indicate that fine-grained controllability results in better reasoning quality.
Blogger's Review: This study significantly enhances the reasoning control capabilities of Large Language Models through the introduction of the SOPHIA method. By breaking away from traditional prompt-based approaches, it demonstrates the potential for dynamic adjustments during the reasoning process, laying a foundation for improving the practicality and efficiency of models in more complex reasoning tasks.