English

Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning

Computation and Language 2025-06-06 v1

Abstract

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based, search-based, and trajectory optimization strategies. We observe that reasoning-optimized models often produce less diverse outputs, which limits TTS effectiveness. To address this, we propose ADAPT (A Diversity Aware Prefix fine-Tuning), a lightweight method that applies prefix tuning with a diversity-focused data strategy. Experiments on mathematical reasoning tasks show that ADAPT reaches 80% accuracy using eight times less compute than strong baselines. Our findings highlight the essential role of generative diversity in maximizing TTS effectiveness.

Keywords

Cite

@article{arxiv.2506.04611,
  title  = {Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning},
  author = {Ho-Lam Chung and Teng-Yun Hsiao and Hsiao-Ying Huang and Chunerh Cho and Jian-Ren Lin and Zhang Ziwei and Yun-Nung Chen},
  journal= {arXiv preprint arXiv:2506.04611},
  year   = {2025}
}

Comments

emnlp 2025 submission

R2 v1 2026-07-01T03:00:34.228Z