Chain of Draft for Software Engineering: Challenges in Applying Concise Reasoning to Code Tasks

TL;DR

This paper extends the Chain of Draft method to software engineering, significantly reducing token usage and costs while maintaining high code quality, thus improving efficiency in LLM-based development workflows.

Contribution

It introduces and evaluates multiple CoD variants tailored for code tasks, demonstrating substantial efficiency gains with minimal quality loss compared to Chain of Thought.

Findings

CoD variants use 55.4% of CoT tokens on average

Achieve approximately 45% reduction in processing time and costs

Maintain over 90% of CoT's code quality metrics

Abstract

Large language models (LLMs) have become vital tools for software development, but they often require verbose intermediate reasoning for complex code tasks, leading to high latency and costs. This research extends the Chain of Draft (CoD) method to software engineering, designing and evaluating multiple CoD variants tailored for code tasks. Through comprehensive experiments on all 300 samples from the SWE-bench benchmark, we found that all CoD variants used significantly fewer tokens than Chain of Thought (CoT), with Baseline CoD being most efficient at 55.4% of CoT's tokens. While this represents substantial efficiency gains - translating to approximately 45% reduction in processing time and API costs - it differs from the extreme 7.6% reported in the original CoD paper for mathematical reasoning. This difference stems from the inherent complexity and context-dependency of software tasks, which require more detailed reasoning to maintain solution quality. Our multi-dimensional quality assessment revealed that CoD variants maintain over 90% of CoT's code quality across key metrics including correctness, compatibility, and maintainability, making them practical alternatives for real-world development scenarios where efficiency matters. This research demonstrates how domain-specific characteristics influence prompting strategy effectiveness and provides a framework for balancing efficiency with solution quality in software engineering applications. Our findings offer practical guidance for optimizing LLM-based development workflows through appropriate prompting strategy selection based on project requirements.