研究人员开发了MARS，一个旨在提高大型语言模型在竞争性编程中性能的多智能体中继系统。与使用通用角色的先前多智能体系统不同，MARS采用由检索增强生成支持的主题专家代理（例如，动态规划、图）。这种专门的方法使MARS在使用Gemma 4在CodeContests基准测试上达到了0.624的通过率，相比直接提示有了显著提高，并降低了与其他系统的成本和方差。 AI
影响 这种专门的多智能体方法可以显著提高LLM在复杂编码任务和其他需要领域专业知识的领域中的性能。
排序理由 该集群描述了一篇详细介绍LLM应用新颖系统的研究论文。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.23918v1 Announce Type: new Abstract: Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of…
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of algorithmic technique to the backbone alone. We…
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of algorithmic technique to the backbone alone. We…
MARS uses retrieval-augmented specialist agents for algorithmic topics to iteratively generate, test, and refine C++ solutions, improving competitive programming pass rates with lower cost.