arXiv cs.AI· Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Junghoon Shin, Minseo Kim·· 4 小时前AI 评分25
Darwin Family 提出 MRI-Trust 加权进化合并实现免训练扩展语言模型推理（论文已撤稿）
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
AI 导读
Darwin Family 是一个免训练的进化合并框架，通过 14 维自适应合并基因组、MRI-Trust Fusion 和 Architecture Mapper 重组已有模型 checkpoint 的潜在能力，无需梯度训练。
正文 · 原文
This paper has been withdrawn by arXiv Admin
No PDF available, click to view other formats
Abstract:We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust parameter; and (iii) an Architecture Mapper that enables cross-architecture breeding between heterogeneous model families. Empirically, the flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training. Across scales from 4B to 35B parameters, Darwin models consistently improve over their parents, support recursive multi-generation evolution, and enable a training-free evolutionary merge that combines Transformer- and Mamba-based components. Together, the Darwin Family demonstrates that diagnostic-guided evolutionary merging is a practical and reproducible alternative to costly post-training pipelines for reasoning-centric language models.
| Comments: | arXiv admin note: This submission has been withdrawn because it does not meet arXiv's research content quality standards |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.14386 [cs.NE] |
| (or arXiv:2605.14386v2 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14386 arXiv-issued DOI via DataCite |
Submission history
From: arXiv Admin [view email]
[v1]
Thu, 14 May 2026 05:09:12 UTC (520 KB)
[v2]
Tue, 3 Nov 2026 22:38:53 UTC (1 KB) (withdrawn)
来源：arXiv cs.AI · arxiv.org