SOURCE-LINKED INTELLIGENCE

Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Best-of-$N$ is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths. However, post-trained reasoning models often suffer from \emph{exploration collapse}, where independent rollouts repeatedly follow similar reasoning paths and limit the gains from increasing the rollout budget. Existing methods alleviate this issue by promoting broader exploration, but do not explicitly guide exploration toward continuations that make meaningful progress, resulting in limited exploration efficiency.

Read original source ↗ Open in workspace

recordType

paper

region

Global