# DEI：演化推理中的多样性用于质量-多样性搜索

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-26 08:00
- AIHOT 分数：59
- AIHOT 链接：https://aihot.virxact.com/items/cmq6rifxv0b4psl5ix3gpdgvr
- 原文链接：https://arxiv.org/abs/2605.27130

## AI 摘要

DEI是一个分布式质量-多样性（QD）搜索框架，将异构大语言模型分配为变异算子，通过非阻塞集体通信共享局部最优解。在Core War基准上，四节点异构集成（GPT-5.4-mini、Claude Sonnet 4.6、GPT-5.2、Claude Haiku 4.5）在相同LLM调用预算下，合并归档QD-Score达45.90（比单节点20.46高124%），覆盖率80.6%（比63.0%高28%），且优于同构集成。首次实证模型多样性而非并行性是分布式LLM-based QD搜索的关键。

## 正文

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 parallel search, which replicates a single model's inductive biases across all workers, DEI treats each LLM's distinct creative prior as a complementary source of behavioral novelty. Extending the Digital Red Queen framework with DEI, nodes share local optimal solutions at the end of each round to seed the next round's population. This creates cross-model adversarial pressure that drives robustness beyond intra-model self-play. Evaluated on the Core War domain, a competitive programming benchmark in which Redcode warrior programs battle inside a simulated machine, a four-node heterogeneous ensemble (GPT-5.4-mini, Claude Sonnet 4.6, GPT-5.2, and Claude Haiku 4.5) achieves 124 percent higher merged-archive QD-Score (45.90 vs. 20.46) and 28 percent higher coverage (80.6 percent vs. 63.0 percent of cells) than a single-node baseline at equal total LLM-call budget. The heterogeneous ensemble also outperforms an equally-budgeted homogeneous ensemble on QD-Score, coverage, and held-out solution generality across all four model families. These results provide the first empirical evidence that model diversity, not merely parallelism, is the key driver of gain in distributed LLM-based QD search.