First Finish Search: Efficient Test-Time Scaling in Large Language Models

TL;DR

This paper introduces First Finish Search (FFS), a simple, training-free decoding method that improves reasoning accuracy in large language models by early stopping once the first completion finishes, reducing inference costs.

Contribution

The paper proposes FFS, a novel parallel decoding strategy that leverages early stopping to enhance reasoning performance without additional training or complex heuristics.

Findings

FFS achieves 82.23% accuracy on AIME datasets, a 15% improvement.

FFS nearly matches OpenAI's o4-mini performance.

Theoretical analysis explains the effectiveness of early stopping in reasoning tasks.

Abstract

Test-time scaling (TTS), which involves dynamic allocation of compute during inference, offers a promising way to improve reasoning in large language models. While existing TTS methods work well, they often rely on long decoding paths or require a large number of samples to be generated, increasing the token usage and inference latency. We observe the surprising fact that for reasoning tasks, shorter traces are much more likely to be correct than longer ones. Motivated by this, we introduce First Finish Search (FFS), a training-free parallel decoding strategy that launches $n$ independent samples and returns as soon as any one completes. We evaluate FFS alongside simple decoding, beam search, majority voting, and budget forcing on four reasoning models (DeepSeek-R1, R1-Distill-Qwen-32B, QwQ-32B and Phi-4-Reasoning-Plus) and across four datasets (AIME24, AIME25-I, AIME25-II and GPQA Diamond). With DeepSeek-R1, FFS achieves $82.23\%$ accuracy on the AIME datasets, a $15\%$ improvement over DeepSeek-R1's standalone accuracy, nearly matching OpenAI's o4-mini performance. Our theoretical analysis explains why stopping at the shortest trace is likely to yield a correct answer and identifies the conditions under which early stopping may be suboptimal. The elegance and simplicity of FFS demonstrate that straightforward TTS strategies can perform remarkably well, revealing the untapped potential of simple approaches at inference time.