Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning

Paper recorded by Signals 4 on 2026-09-22 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-22 on arXiv · recorded by Signals 4 on 2026-09-23

Category: cs.AI · 人工智能 · first seen 2026-09-23

Abstract

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 c

Read on arXiv →