SOURCE-LINKED INTELLIGENCE

Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independent solutions and hope one is correct. Because such sampling explores only through local decoding noise, it tends to produce many near duplicate attempts rather than genuinely different ideas. We ask whether exploration can instead be steered at a semantic level, by first sampling problem specific concepts, hints, or strategies and then conditioning answer generation on them. We refine this into a simple, more explora

Read original source ↗ Open in workspace

recordType

paper

region

Global