Constructing a Pareto set is pivotal for navigating the capability--efficiency trade-offs in Large Language Models (LLMs). However, existing merging techniques remain inadequate for this task. Coarse-grained, model-level methods yield only a sparse set of suboptimal solutions, while fine-grained, layer-wise approaches suffer from the curse of dimensionality, rendering the search space computationally intractable. To resolve this dichotomy, we propose Structural Importance Prior Bayesian Model Merging (SIP-BMM), a framework that automatically constructs the LLM Pareto set. SIP-BMM renders high-dimensional layer-wise search tractable by introducing an importance-aware Sparse Axis-Aligned Subspace Bayesian Optimization (SAASBO) strategy. By leveraging a structural importance prior derived from task-vector differences, our method guides SAASBO to automatically identify critical layers, thereby dramatically reducing the effective dimensionality without sacrificing the granularity of full-model control. The entire process is automated within an evolutionary loop driven by the Log-Noisy Expected Hypervolume Improvement ($q$NEHVI) acquisition function. Experiments demonstrate that SIP-BMM discovers a stronger and denser Pareto front than competitive baselines, enabling agile model selection tailored to diverse operational constraints. Code is available at: https://github.com/MiLab-HITSZ/2026-SIPBMM.

翻译：构建帕累托前沿对于权衡大语言模型（LLMs）的能力与效率至关重要。然而，现有的模型融合技术对此任务仍显不足。粗粒度的模型级方法仅能产生稀疏的次优解集，而细粒度的分层方法则受困于维度灾难，导致搜索空间在计算上难以处理。为解决这一困境，我们提出了结构重要性先验贝叶斯模型融合（SIP-BMM），一个能自动构建LLM帕累托前沿的框架。SIP-BMM通过引入一种重要性感知的稀疏轴对齐子空间贝叶斯优化（SAASBO）策略，使得高维分层搜索变得可行。该方法利用从任务向量差异中推导出的结构重要性先验，引导SAASBO自动识别关键层，从而在不牺牲全模型控制粒度的情况下，显著降低有效维度。整个过程在一个由对数噪声期望超体积改进（$q$NEHVI）采集函数驱动的进化循环中自动进行。实验表明，与竞争基线相比，SIP-BMM能发现更强且更密集的帕累托前沿，从而能够根据多样化的操作约束进行敏捷的模型选择。代码发布于：https://github.com/MiLab-HITSZ/2026-SIPBMM。