Papers
Topics
Authors
Recent
Search
2000 character limit reached

Provable Test-Time Scaling for Beam Search in LLM Reasoning

Published 29 Sep 2026 in cs.LG and cs.AI | (2609.38672v1)

Abstract: Beam-search-based test-time methods provide an effective way to improve LLM performance on long-horizon generation by pruning invalid reasoning paths early, leading to significantly improved reasoning efficiency and more favorable test-time cost scaling. Despite strong empirical success, the theoretical understanding of beam search remains limited. In this paper, we study the test-time compute guarantee of the commonly used beam search framework that uses the model's internal log-likelihood for intermediate scoring, while relying on an external reward model only after a complete response is generated. We first establish a lower bound for vanilla beam search, showing that at least Ω(C⋆(x)2)Ω(C^\star(x)^2) samples are required for the optimal response to survive, where C⋆(x)C^\star(x) is the token-level coverage coefficient for prompt xx. This motivates our modified confidence-filtered beam search (CF-Beam), which reduces the sufficient coverage dependence from quadratic to nearly linear under prefix competitiveness, for fixed horizon, gap, and target accuracy. We then show that the regret of CF-Beam is upper-bounded by the probability of rare failure events and the reward estimation error scaled by a path-level coverage coefficient, where the rare-failure term vanishes as per-step sampling increases. Our results highlight a fundamental advantage of beam search over sequence-level inference methods such as Best-of-N and Best-of-Majority. While the guarantees of these approaches typically involve coverage coefficients that grow exponentially with the horizon LL, CF-Beam controls the dominant search-induced term through a token-level coverage coefficient that scales polynomially with LL. Our numerical experiments further confirm that beam search is more robust on hard instances and under increasing reasoning horizons.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.