Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
Year: 2026
Type: conference-paper
Abstract: Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking."Existing solutions via reinforcement learning (RL) typically penalize generated tokens to promote conciseness.However, these methods encounter two challenges: responses with fewer tokens do not always correspond to fewer reasoning steps, and models may develop hacking behavior in later stages of training by discarding reasoning steps to minimize token usage.In this work, we introduce Step Pruner (SP), an RL framework that steers LRMs toward more efficient reasoning by favoring compact reasoning steps.Our step-aware reward function prioritizes correctness while imposing penalties for redundant steps, and withholds rewards for incorrect responses to prevent the reinforcement of erroneous reasoning.Moreover, we propose a dynamic stopping mechanism to prevent hacking behavior caused by step merging.Extensive experiments across four reasoning benchmarks demonstrate that SP achieves state-of-the-art accuracy while significantly reducing response length.For instance, on AIME24, SP reduces token usage by 69.7%.
Authors: Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He
Institutions: Future Academy, Xi'an Jiaotong University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4414969874