一篇新的研究论文介绍了一种名为DEI的分布式质量-多样性搜索框架，该框架利用异构大型语言模型（LLMs）作为变异算子。这种方法将每个LLM独特的创造性先验视为新颖性的互补来源，并通过跨模型对抗性压力来增强鲁棒性。在对核心战争领域的评估中，一个四节点的异构集成在QD-Score和覆盖率方面显著优于单节点和同构集成，证明了模型多样性（而不仅仅是并行性）对于基于LLM的分布式QD搜索的收益至关重要。 AI
影响 证明了在分布式搜索框架中利用多样化的LLM可以显著提高性能，超越简单的并行性。
排序理由 该集群包含一篇详细介绍新研究框架及其评估的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.27130v1 Announce Type: cross Abstract: We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-bloc…
We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking collective operations. Unlike homogeneous par…
We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking collective operations. Unlike homogeneous par…