EliteTable：面向可执行控制策略的自改进程序搜索
原标题：EliteTable: Self-Improving Program Search for Executable Control Policies
AI 摘要
该论文提出 EliteTable，一种由大语言模型引导的自改进程序搜索算法，使用固定容量的高分方案表来指导新提案、编辑和重组。在六个 Gymnasium 控制任务上各进行十代、每代五十个候选的评估，每个任务独立初始化搜索十次。结果显示六个任务的候选分数中位数均上升，五个任务选出的优胜者搜索分数中位数上升，四个任务中全部十次配对留出端点均有改善，但 Acrobot-v1 有六次搜索在留出回合上下降。作者指出仍需比较和消融实验来确定 EliteTable 的相对性能及各组件贡献。
正文节选
EliteTable: Self-Improving Program Search for Executable Control Policies Abstract—EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new proposals, edits of existing solutions, and remixes of several solutions. Performance was evaluated across six Gymnasium control tasks, each with ten generations and fifty candidate slots per generation. Each task was evaluated across ten independent