ImprovEvolve:盆地跳跃与LLM引导的进化搜索
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search
AI总结:
ImprovEvolve通过进化三个专用算子(初始化、局部改进、扰动)降低LLM认知负担,通过迭代局部改进和扰动实现盆地跳跃搜索,在六边形堆叠和球面码问题中取得新成果。
摘要:
LLM引导的进化计算,特别是AlphaEvolve,在解决挑战性优化问题中发现新数学构造方面取得了显著成功。标准方法是进化一个单一程序直接输出候选解。我们提出了ImprovEvolve,一种算法替代方法,大幅降低LLM的认知负担。不是提示模型生成端到端优化器,而是进化一个包含初始化、局部改进和扰动三个专用算子的程序。然后通过迭代应用局部改进和强度调度的扰动来接近最优解,有效实现LLM进化子程序驱动的盆地跳跃搜索。在六边形嵌套堆叠问题中,ImprovEvolve发现11、12、15和16个六边形的新最先进堆叠,以及在经过最小专家调整代码后,14、17和23个六边形的改进。对于第二个自相关不等式,进化和人类可扩展的程序将下限从0.96102提升到0.96258。对于球面码,ImprovEvolve程序在90个随机选择的多样化最先进球面码中,将大多数的最佳最大余弦值降低,最大相对改进达2.4%。
英文摘要:
LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iteratively applying local improvements and intensity-scheduled perturbations, effectively driving a basin-hopping search with LLM-evolved subroutines. For hexagon in hexagon packing, ImprovEvolve discovers new state-of-the-art packings of 11, 12, 15, and 16 hexagons, and additionally for 14, 17, and 23 hexagons after minimal expert tuning of the generated code. For the second autocorrelation inequality, the evolved and human-scaled program pushes the lower bound from 0.96102 to 0.96258. For spherical codes, the ImprovEvolve program lowers the best-known maximum cosine for the majority of 90 randomly chosen diverse state-of-the-art spherical codes, achieving relative improvements of up to 2.4%.
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。