从入档到留存：预测 Quality-Diversity 搜索中的持久性后代
From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search
AI 导读
一项研究考察 Quality-Diversity（QD）搜索中的信用分配问题，测试个体繁殖前可获得的信号能否区分仅进入档案的后代与多代后仍被保留的后代。在平面机械臂基准和两个机器人运动任务上，谱系深度是最清晰的信号，且其留存区分度随种群容量增大而增强。但据此偏向父代选择并不提升搜索效果：中等偏置与均匀采样持平，强偏置反而降低 QD 分数。
正文 · 原文
Abstract:Automated failure discovery can be framed as a diversity problem: the objective is to expose distinct ways a system fails rather than a single critical adversarial case. Yet uniform parent sampling provides no way to allocate search effort toward individuals likely to produce durable archive contributions. We study this credit assignment problem in an unstructured Quality-Diversity (QD) archive, testing whether signals available before an individual has reproduced distinguish offspring that merely enter the archive from those still retained generations later. Across a planar-arm benchmark and two robotic-locomotion tasks, the same signals are often associated with entry and persistence in opposite directions. In particular, lineage depth is the clearest such signal, and its persistence discrimination grows with population capacity, which is associated with lower turnover. Biasing parent selection toward the signals with the strongest measured association to survival nevertheless does not improve search: moderate bias matches uniform sampling, and strong bias reduces QD-score.
| Comments: | Accepted at the NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems (EvoRobust) |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06522 [cs.NE] |
| (or arXiv:2611.06522v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06522 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Corrado Calamita [view email]
[v1]
Wed, 4 Nov 2026 13:47:40 UTC (359 KB)
来源：arXiv cs.AI · arxiv.org