让代码生成与计划协同进化，动态决策提升效率与质量
CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation
- 计划与代码模块动态协作，按需决定执行顺序
- 在复杂任务上性能提升11%-20%，API调用减少4-10次/次执行
- 适合追求高效可靠代码生成的开发者与研究者
自动化代码生成仍是软件工程中的持续挑战，传统多智能体框架常受限于静态规划、独立执行、高计算开销及对复杂任务适应性差。本文提出CollabCoder，一种基于动态多智能体协作的计划-代码协同进化框架。其核心思想是设计计划模块与代码模块间的协同决策机制，以决定调试过程中由哪个模块执行。在多个主流基准上的实验证明，CollabCoder在各类任务中持续提升代码质量与鲁棒性。尤为重要的是，该方法在性能上达到或超越当前最先进水平的同时，显著降低计算开销，且随着基准难度提升，效率优势更明显。在更具挑战性的LiveCodeBench和xCodeEval上，相比强基线模型性能提升11%-20%，平均每次执行减少4-10次API调用。
原文摘要 · Abstract (English)
Automated code generation remains a persistent challenge in software engineering, as conventional multi-agent frameworks are often constrained by static planning, isolated execution, high computational overhead, and limited adaptability to complex tasks. This paper introduces CollabCoder, a novel Plan-Code Co-Evolution framework that improves code generation through dynamic multi-agent collaboration. The core idea is to design a collaborative decision-making process between the plan module and the code module to decide which module should be executed for the debugging process. Extensive experiments on widely used benchmarks demonstrate that CollabCoder consistently improves code quality and robustness across tasks. Importantly, CollabCoder achieves performance comparable to or exceeding current state-of-the-art methods while reducing computational overhead, with efficiency gains becoming more pronounced as benchmark difficulty increases. On the more challenging LiveCodeBench and xCodeEval benchmarks, our approach improves performance by 11-20% over strong baselines while reducing the number of API calls by an average of 4-10 per execution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。