让代码生成模型自动进化，动态调整流程与底层模型。
SEMAG: Self-Evolutionary Multi-Agent Code Generation
- 分阶段模拟人类编程，按任务难度自适应调整流程
- 在CodeContests上比旧方法高3.3%准确率，达52.6%新纪录
- 适合追求自动化、持续进化的代码生成研究者
大型语言模型在处理复杂编程任务方面已取得显著进展。然而，现有方法依赖人工模型选择和固定工作流，难以适应任务复杂度的变化。为此，我们提出SEMAG——一种自演化多智能体代码生成框架，模仿人类编程实践。该框架将编程任务分解为规划、编码、调试和讨论等阶段，并根据任务难度自适应调整工作流。其自演化智能体可实时访问最新模型并自动升级核心模型。SEMAG在多个基准测试中达到新的最优性能。使用相同核心模型时，相较于先前方法在CodeContests上提升3.3%的Pass@1准确率；当结合自演化模型选择机制自动识别最优核心模型时，准确率可达52.6%，充分展现框架的有效性与对演进中LLM能力的适应性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task complexities. To address this, we propose SEMAG, a Self-Evolutionary Multi-Agent code Generation framework that mimics human coding practices. It decomposes programming tasks into stages, including planning, coding, debugging, and discussion, while adapting workflows to task difficulty. Its self-evolutionary agents can access the latest models in real time and automatically upgrade the backbone model. SEMAG sets new state-of-the-art Pass@1 accuracy across benchmarks. Using identical backbone models, SEMAG outperforms prior methods by 3.3% on CodeContests. When augmented with self-evolutionary model selection that automatically identifies optimal backbones, SEMAG reaches 52.6%, showcasing both framework effectiveness and adaptability to evolving LLM capabilities.
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。