arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.05949cs.AIcs.SE
收藏

MAS-Algorithm: 一个基于多智能体系统的算法问题求解工作流

MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System

Peking University(北京大学);Alibaba Group(阿里巴巴集团);Huazhong University of Science and Technology(华中科技大学)

Yuliang Xu, Xiang Xu, Yao Wan, Hu Wei, Tong Jia

AI总结:

本文提出MAS-Algorithm,通过多智能体工作流提升算法问题求解能力,实验显示在多个模型上均取得显著提升,包括接受率提升6.48%和LiveCodeBench-Pro上的4.72%提升。

摘要:

算法问题求解是评估AI编码系统结构推理能力的严格测试场,直接反映模型在复杂场景中进行结构推理的能力。现有方法主要依赖模型中心策略,如架构修改和数据扩展,成本高且可解释性差。替代方法利用外部工具或提示技术(如链式思考)往往碎片化且缺乏统一框架。本文提出MAS-Algorithm,一个受竞赛程序员和算法工程师实践启发的系统性多智能体工作流。我们的框架将端到端求解过程分解为模块化阶段,实现结构推理、工具集成和智能体间灵活协调。设计强调严谨性和可扩展性,使其能够推广到多样化的问题类型。在自建基准上的实验结果表明,多个Qwen系列模型均取得一致提升,平均接受率提升6.48%。相比之下,相同数据上的参数高效微调仅带来0.89%的微小提升。我们进一步在LiveCodeBench-Pro上观察到4.72%的提升,同时在其他准确性和效率指标上也取得一致提升。除了性能提升,我们还进行了全面分析以更好地理解工作流内的推理过程,包括错误模式和跨场景行为。我们进一步进行了定制替换和消融研究以探索框架的上限,显示单个智能体可带来高达27.7%的改进。这些结果突显了MAS-Algorithm在推动AI驱动算法推理方面的强大潜力。

英文摘要:

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches predominantly rely on model-centric strategies, such as architectural modifications and data scaling, which are costly and offer limited interpretability. Alternative methods leveraging external tools or prompting techniques (e.g., chain-of-thought) are often fragmented and lack a unified framework. In this paper, we propose MAS-Algorithm, a systematic multi-agent workflow for algorithmic problem solving inspired by the practices of competitive programmers and algorithm engineers. Our framework decomposes the end-to-end solving process into modular stages, enabling structured reasoning, tool integration, and flexible coordination among agents. The design emphasizes both rigor and extensibility, allowing it to generalize across diverse problem types. Experimental results on a self-constructed benchmark demonstrate consistent improvements across multiple Qwen series models, achieving an average gain of 6.48% in acceptance rate. In contrast, parameter-efficient fine-tuning on the same data yields only a marginal improvement of 0.89%. We further observe a 4.72% gain on LiveCodeBench-Pro, along with consistent improvements across additional accuracy and efficiency metrics. Beyond performance gains, we conduct comprehensive analyses to better understand the reasoning process within the workflow, including error patterns and cross-scenario behaviors. We further perform customized replacement and ablation studies to explore the upper bound of the framework, showing that individual agents can contribute improvements of up to 27.7%. These results highlight the strong potential of MAS-Algorithm for advancing AI-driven algorithmic reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑