arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07970cs.AI
收藏

通过基于大语言模型的进化分阶段设计推进自动化算法设计

Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs

National Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室);School of Artificial Intelligence, Nanjing University, China(南京大学人工智能学院);Huawei Noah’s Ark Lab, China(华为诺亚实验室)

Chen Lu, Ke Xue, Chengrui Gao, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, Chao Qian, Zhi-Hua Zhou

AI总结:

本文提出EvoStage方法,通过分阶段进化设计提升自动化算法设计效率,实现超越人类专家和现有LLM方法的性能。

摘要:

随着人类科学和技术的迅速发展,工业场景中的问题变得日益复杂,给传统算法设计带来了重大挑战。利用大语言模型(LLM)进行自动化算法设计成为一种有前景的解决方案,但目前采用的黑盒建模方法使LLM无法意识到目标问题的内在机制,导致设计出现幻觉。本文介绍了一种新的进化范式——进化分阶段算法设计(EvoStage),该范式弥合了工业级算法设计对严格要求与基于LLM的算法设计方法之间的差距。受CoT的启发,EvoStage将算法设计过程分解为连续、可管理的阶段,并整合实时中间反馈以迭代优化算法设计方向。为进一步减少算法设计空间并避免陷入局部最优,我们引入了多智能体系统和

英文摘要:

With the rapid advancement of human science and technology, problems in industrial scenarios are becoming increasingly challenging, bringing significant challenges to traditional algorithm design. Automated algorithm design with LLMs emerges as a promising solution, but the currently adopted black-box modeling deprives LLMs of any awareness of the intrinsic mechanism of the target problem, leading to hallucinated designs. In this paper, we introduce Evolutionary Stagewise Algorithm Design (EvoStage), a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods. Drawing inspiration from CoT, EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions. To further reduce the algorithm design space and avoid falling into local optima, we introduce a multi-agent system and a "global-local perspective" mechanism. We apply EvoStage to the design of two types of common optimizers: designing parameter configuration schedules of the Adam optimizer for chip placement, and designing acquisition functions of Bayesian optimization for black-box optimization. Experimental results across open-source benchmarks demonstrate that EvoStage outperforms human-expert designs and existing LLM-based methods within only a couple of evolution steps, even achieving the historically state-of-the-art half-perimeter wire-length results on every tested chip case. Furthermore, when deployed on a commercial-grade 3D chip placement tool, EvoStage significantly surpasses the original performance metrics, achieving record-breaking efficiency. We hope EvoStage can significantly advance automated algorithm design in the real world, helping elevate human productivity.

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。

↑