Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization

TL;DR

CoSMo is a framework that enhances reasoning efficiency in large models by dynamically refining reasoning chains through split-merge optimization, reducing redundancy and maintaining coherence.

Contribution

It introduces a novel split-merge algorithm and structure-aligned reinforcement learning to improve reasoning efficiency without sacrificing coherence.

Findings

Achieves 3.3 points higher accuracy on benchmarks.

Reduces segment usage by 28.7% on average.

Demonstrates superior performance across multiple benchmarks.

Abstract

While Large Reasoning Models (LRMs) have demonstrated impressive capabilities in solving complex tasks through the generation of long reasoning chains, this reliance on verbose generation results in significant latency and computational overhead. To address these challenges, we propose \textbf{CoSMo} (\textbf{Co}nsistency-Guided \textbf{S}plit-\textbf{M}erge \textbf{O}ptimization), a framework designed to eliminate structural redundancy rather than indiscriminately restricting token volume. Specifically, CoSMo utilizes a split-merge algorithm that dynamically refines reasoning chains by merging redundant segments and splitting logical gaps to ensure coherence. We then employ structure-aligned reinforcement learning with a novel segment-level budget to supervise the model in maintaining efficient reasoning structures throughout training. Extensive experiments across multiple benchmarks and backbones demonstrate that CoSMo achieves superior performance, improving accuracy by \textbf{3.3} points while reducing segment usage by \textbf{28.7\%} on average compared to reasoning efficiency baselines.