cs.AINov 11, 2026

Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling

Authors: Jie Ren, Jonathan Rosenfeld, Neil Thompson

Organizations: MIT CSAIL, MIT FutureTech

Abstract

Parallel test-time scaling (TTS) has been shown to enhance reasoning in large language models by generating and aggregating multiple independent reasoning paths. Internal confidence scores can further improve this process by identifying paths of varying quality. However, existing methods remain computationally inefficient, as low-quality paths are fully expanded before being evaluated. In this work, we aim to improve the use of internal confidence signals for better model performance and computational efficiency. We begin by offering a new perspective on the role of confidence in aggregation, showing that it is most impactful for questions near the decision boundary. Notably, when amplified by multi-sample aggregation, even small confidence signals derived from short prefixes can meaningfully influence outcomes in these boundary cases. Building on this insight, we introduce Prefix-Guided Sampling (PreG), a method that reallocates computation by first generating short prefixes, ranking them using internal confidence scores, and then completing only the most promising candidates. This strategy reduces token usage while maintaining gains in path quality. We provide theoretical analysis demonstrating that, under a fixed compute budget, PreG strengthens the effective signal by widening the decision boundary margin. Empirically, our method consistently outperforms standard parallel TTS approaches across benchmarks, while significantly improving token efficiency and reducing overall computation.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

    May 26, 2026Xinglin Wang, Hao Lin, Shaoxiong Feng +9Inference-Time SearchTest-Time Scaling

  2. Efficient Test-Time Scaling via Temporal Reasoning Aggregation

    Apr 19, 2026Jiakun Li, Xingwei He, Kefan Li +3Test-Time ScalingEfficient Language Model Inference

  3. Planned Test-Time Scaling with Coordinated Reasoning Paths

    Sep 23, 2026Xueqing Wu, Langxing Bai, Hritik Bansal +5RL for Language Model ReasoningTest-Time Scaling