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.
Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间科学与工程学院);Key Laboratory of Cyberspace Security, Ministry of Education(教育部网络空间安全重点实验室);Hubei Key Laboratory of Distributed System Security(湖北省分布式系统安全重点实验室)
TACO: Topics in Algorithmic COde generation dataset
Beijing Academy of Artificial Intelligence(北京人工智能研究院);School of Information Science and Engineering, Shandong Normal University(山东师范大学信息科学与工程学院);Peking University(北京大学)
Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models
Icahn School of Medicine at Mount Sinai(西奈山伊坎医学院);Mount Sinai Hospital(西奈山医院);Boston Children’s Hospital(波士顿儿童医院);Harvard Medical School(哈佛医学院);University of Pittsburgh School of Medicine(匹兹堡大学医学院)
Toward Causal-Visual Programming: Enhancing Agentic Reasoning in Low-Code Environments
School of Information \& Computer Science University of California, Irvine Irvine, CA, USA;Independent Researcher;University of Texas at Dallas Dallas, TX, USA;Georgia Institute of Technology Atlanta, GA, USA
Leveraging Large Language Models to Build and Execute Computational Workflows
Universidad San Francisco de Quito(基多圣弗朗西斯科大学);University of Missouri(密苏里大学);National Center for Supercomputing Applications(美国国家超级计算应用中心);University of Illinois Urbana Champaign(伊利诺伊大学厄巴纳-香槟分校)
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
New York University(纽约大学);Princeton University(普林斯顿大学);University of California San Diego(加利福尼亚大学圣地亚哥分校);University of Washington(华盛顿大学);Canyon Crest Academy(峡谷克雷斯特学院);University of Waterloo(滑铁卢大学);McGill University(麦吉尔大学)