Lune

ACL Findings2025

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation

Huimin Xu, Xin Mao, Feng-Lin Li, Xiaobao Wu, Wang Chen, Wei Zhang, Anh Tuan Luu

Abstract

Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte Carlo simulations, remain computationally expensive. In this paper, we introduce Step COmpression for Process Estimation (SCOPE), a novel compression-based approach that significantly reduces annotation costs. We first translate natural language reasoning steps into code and normalize them through Abstract Syntax Tree, then merge equivalent steps to construct a prefix tree. Unlike simulation-based methods that waste numerous samples on estimation, SCOPE leverages a compression-based prefix tree where each root-to-leaf path serves as a training sample, reducing the complexity from O(N M K) to O(N ). We construct a large-scale dataset containing 196K samples with only 5% of the computational resources required by previous methods. Empirical results demonstrate that PRMs trained on our dataset consistently outperform existing automated annotation approaches on both Best-of-N strategy and ProcessBench 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Let's Verify Step by Step cites Solving Quantitative Reasoning Problems with Language Models
  • SGLang: Efficient Execution of Structured Language Model Programs cites DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on16

  1. Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
  2. Solving Quantitative Reasoning Problems with Language ModelsAitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer et al.NeurIPS 2022 · 2,039 citations
  3. SGLang: Efficient Execution of Structured Language Model ProgramsLianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun et al.NeurIPS 2024 · 1,586 citations
  4. DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented ScaleReza Yazdani Aminabadi, Samyam Rajbhandari, Ammar Ahmad Awan, Cheng Li et al.SC 2022 · 276 citations
  5. ProcessBench: Identifying Process Errors in Mathematical ReasoningChujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin et al.ACL 2025 · 209 citations

Related papers

  1. SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward LearningYuyang Ding, Xinyu Shi, Juntao Li, Xiaobo Liang et al.NeurIPS 2025 · 10 citations
  2. Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language ModelsTeng Wang, Zhangyi Jiang, Zhenqi He, Hailei Gong et al.ACL Findings 2026 · 1 citation
  3. AdaptiveStep: Automatically Dividing Reasoning Step through Model ConfidenceYuliang Liu, Junjie Lu, Chaofeng Qu, Zhaoling Chen et al.ICML 2025
  4. An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical ReasoningWei Sun, Qianlong Du, Fuwei Cui, Jiajun ZhangACL 2025 · 15 citations
  5. Efficient Process Reward Modeling via Contrastive Mutual InformationNakyung Lee, Sangwoo Hong, Jungwoo LeeACL 2026 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines