发表机构
Santa Clara University（圣克拉拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出组件感知反馈机制，通过记录程序组件编辑与指标差异的归因记忆，提升LLM引导进化搜索的效率，在重排序任务上以更少预算达到更优质量。
AI 中文摘要
LLM引导的进化搜索可以发现复杂程序，但现有方法大多只保存候选程序和适应度分数，而丢弃了哪些组件编辑产生了哪些适应度指标变化的信息。现有方法迫使变异器LLM从杂乱的历史记录中推断先前编辑的效果，使得程序搜索缓慢且不稳定。这对于本地可服务的LLM进化多组件系统尤其如此。我们引入了组件感知反馈，它将每个评估的程序与其父程序进行比较，识别发生变化的组件，并将它们与相关的指标差异记录到归因记忆中，供后续变异读取。该记忆以两种参考框架保存每次变化：相对于其来源父程序的局部框架，以及相对于种子程序的全局框架，这既显示了变化的即时效果，也显示了自种子以来的累积进展。我们在LLM重排序这一多目标优化问题上研究了该方法，该问题中多阶段流水线必须平衡质量与服务成本。在十二个\ extsc{Bright}数据集上，我们的方法在搜索预算中位数三分之一处达到最强基线的最终质量，并在保留的nDCG@10上最终高出7.2%；在成本感知目标下，它找到的流水线平均更准确，同时每个查询使用的令牌减少11%，表明组件感知反馈是更高效自进化系统的一个有前景的方向。
英文摘要
LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from cluttered histories, making program search slow and unstable. This is especially true for locally servable LLMs to evolve multi-component systems. We introduce component-aware feedback, which compares each evaluated program with its parent, identifies the components that changed, and logs them with the associated metric differences into an attribution memory that later mutations read. The memory keeps each change in two reference frames, local against the parent it came from and global against the seed program, which shows both the immediate effect of a change and the cumulative progress made since the seed. We study this on LLM reranking, a multi-objective optimization problem where a multi-stage pipeline must balance quality against serving cost. Across twelve \textsc{Bright} datasets, our method reaches the strongest baseline's final quality after a median of one third of the search budget and ends 7.2\% higher in held-out nDCG@10, and under a cost-aware objective it finds pipelines that are on average more accurate while using 11\% fewer tokens per query, showing component-aware feedback to be a promising direction for more efficient self-evolving systems.
