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-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.
| Comments: | Accepted to ICML 2026 Workshop Scalable Learning and Optimization for Efficient Multimodal AI Agents (SCALE) |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.27130 [cs.LG] |
| (or arXiv:2605.27130v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.27130 arXiv-issued DOI via DataCite (pending registration) |
From: John Donaghy [view email]
[v1]
Tue, 26 May 2026 15:00:57 UTC (417 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。