发表机构
Practical Systems（普拉克蒂卡尔系统公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出Discovery Loop系统，用LLM迭代演化优化算法，将其应用于Packomania圆填充基准，在15次迭代内以约28美元成本打破10项最优记录，推动自动化科学发现民主化。
AI 中文摘要
我们提出了Discovery Loop，这是一个利用大语言模型（LLM）迭代演化优化算法的轻量系统。从一个简单的初始求解器出发，LLM在结果记分板和先前思路历史的引导下，提出算法改进方案。每个候选方案由独立验证器评估；改进方案被保留，失败方案被丢弃。将该系统应用于Packomania圆填充基准（csqv：在单位正方形中最大化N个可变半径圆的半径之和），系统改进了N在101-114范围内的10个值的已知最优解，较之前的记录获得了2.4%-5.4%的提升，所有改进均在15次迭代内完成，总LLM成本为27.72美元。这些结果已被Packomania独立认可。我们描述了该方法，分析了成本效率动态（包括自适应平台检测机制），并讨论了其对自动化科学发现民主化的意义。
英文摘要
We present Discovery Loop, a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms. Starting from a simple seed solver, the LLM proposes algorithmic improvements guided by a scoreboard of results and a history of prior ideas. Each candidate is evaluated against an independent verifier; improvements are kept and failures discarded. Applied to the Packomania circle-packing benchmark (csqv: maximize the sum of radii of N variable-radius circles in the unit square), the system improved the best known solutions for 10 values of N in the range 101-114, with gains of 2.4%-5.4% over prior records, all within 15 iterations and at a total LLM cost of $27.72. These results have been independently accepted by Packomania. We describe the method, analyze cost-efficiency dynamics including an adaptive plateau-detection mechanism, and discuss implications for democratizing automated scientific discovery.
Comments8 pages. Code and solutions: https://github.com/ucsandman/discovery-loop
