通过多目标优化，让代码生成智能体更高效更环保。
GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization
- 用多目标优化寻找最佳超参数与提示模板组合
- 减少37.7%运行量，正确率提升，效率提升135倍
- 适合关注代码生成可持续性的工业部署团队
由大模型驱动的代码生成智能体在工业部署中面临严重的可持续性与可扩展性挑战，单次运行消耗超过10万token，环境成本可能超过优化收益。本文提出GA4GC，首个系统性优化智能体运行效率（更绿色的智能体）与代码质量（更绿色的代码）权衡的框架，通过发现帕累托最优的智能体超参数与提示模板组合实现平衡。在SWE-Perf基准上的评估显示，范数体积提升达135倍，智能体运行时间减少37.7%的同时提升代码正确性。研究发现温度是最重要的超参数，并为工业部署中平衡智能体可持续性与代码优化效果提供了可操作策略。
原文摘要 · Abstract (English)
Coding agents powered by LLMs face critical sustainability and scalability challenges in industrial deployment, with single runs consuming over 100k tokens and incurring environmental costs that may exceed optimization benefits. This paper introduces GA4GC, the first framework to systematically optimize coding agent runtime (greener agent) and code performance (greener code) trade-offs by discovering Pareto-optimal agent hyperparameters and prompt templates. Evaluation on the SWE-Perf benchmark demonstrates up to 135x hypervolume improvement, reducing agent runtime by 37.7% while improving correctness. Our findings establish temperature as the most critical hyperparameter, and provide actionable strategies to balance agent sustainability with code optimization effectiveness in industrial deployment.
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。