# 及时止损！面向高效并行推理的早期路径剪枝学习

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-17 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo6mad9l04tmsl4rxt1m6e3v
- 原文链接：https://arxiv.org/abs/2604.16029

## AI 摘要

针对并行推理中早期错误导致无效路径的高成本问题，研究团队提出首个路径剪枝系统化分类框架，并开发了基于可学习内部信号的STOP（Super TOken for Pruning）方法。在1.5B至20B参数的大型推理模型评估中，该方法在固定计算预算下将GPT-OSS-20B在AIME25基准的准确率从84%提升至近90%，有效性与效率均优于现有基线。研究同时提供了形式化的经验部署指南。

## 正文

Parallel reasoning enhances Large Reasoning Models (LRMs) but incurs prohibitive costs due to futile paths caused by early errors. To mitigate this, path pruning at the prefix level is essential, yet existing research remains fragmented without a standardized framework. In this work, we propose the first systematic taxonomy of path pruning, categorizing methods by their signal source (internal vs. external) and learnability (learnable vs. non-learnable). This classification reveals the unexplored potential of learnable internal methods, motivating our proposal of STOP (Super TOken for Pruning). Extensive evaluations across LRMs ranging from 1.5B to 20B parameters demonstrate that STOP achieves superior effectiveness and efficiency compared to existing baselines. Furthermore, we rigorously validate the scalability of STOP under varying compute budgets - for instance, boosting GPT-OSS-20B accuracy on AIME25 from 84% to nearly 90% under fixed compute budgets. Finally, we distill our findings into formalized empirical guidelines to facilitate optimal real-world deployment. Code, data and models are available at https://bijiaxihh.github.io/STOP