BAMBO: Construct Ability and Efficiency LLM Pareto Set via Bayesian Adaptive Multi-objective Block-wise Optimization

• URL: http://arxiv.org/abs/2512.09972v2
• Date: Fri, 12 Dec 2025 05:23:18 GMT
• Title: BAMBO: Construct Ability and Efficiency LLM Pareto Set via Bayesian Adaptive Multi-objective Block-wise Optimization
• Authors: Kesheng Chen, Wenjian Luo, Zhenqian Zhu, Yamin Hu, Yiya Xi,
• Abstract summary: BAMBO (Bayesian Adaptive Multi-objective Block-wise Optimization) is a novel framework that automatically constructs the Large Language Models (LLMs)<n>Formulated as a 1D clustering problem, this strategy leverages a dynamic programming approach to optimally balance intra-blockvolume and inter-block information distribution.
• Score: 4.196004665145396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 BAMBO (Bayesian Adaptive Multi-objective Block-wise Optimization), a novel framework that automatically constructs the LLM Pareto set. BAMBO renders the search tractable by introducing a Hybrid Optimal Block Partitioning strategy. Formulated as a 1D clustering problem, this strategy leverages a dynamic programming approach to optimally balance intra-block homogeneity and inter-block information distribution, thereby dramatically reducing dimensionality without sacrificing critical granularity. The entire process is automated within an evolutionary loop driven by the q-Expected Hypervolume Improvement (qEHVI) acquisition function. Experiments demonstrate that BAMBO discovers a superior and more comprehensive Pareto frontier than baselines, enabling agile model selection tailored to diverse operational constraints. Code is available at: https://github.com/xin8coder/BAMBO.

Related papers

• Divide and Learn: Multi-Objective Combinatorial Optimization at Scale [41.78439888126577]
  Multi-objective optimization seeks solutions over exponentially large discrete spaces.<n>We reformulate it as an online learning problem over a decomposed decision space, solving position-wise bandit subproblems.<n>On standard benchmarks, our method achieves 80--98% of specialized solvers performance.
  arXiv  Detail & Related papers  (2026-02-11T20:29:35Z)
• MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions [14.595244541373456]
  MOBO-OSD is a multi-objective Bayesian Optimization algorithm designed to generate a diverse set of optimal solutions.<n>By employing a well-distributed set of OSDs, MOBO-OSD ensures broad coverage of the objective space, enhancing both solution diversity and hypervolume performance.<n>We demonstrate that MOBO-OSD consistently outperforms the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2025-10-23T09:42:41Z)
• LLM4CMO: Large Language Model-aided Algorithm Design for Constrained Multiobjective Optimization [54.35609820607923]
  Large language models (LLMs) offer new opportunities for assisting with algorithm design.<n>We propose LLM4CMO, a novel CMOEA based on a dual-population, two-stage framework.<n>LLMs can serve as efficient co-designers in the development of complex evolutionary optimization algorithms.
  arXiv  Detail & Related papers  (2025-08-16T02:00:57Z)
• Pareto Multi-Objective Alignment for Language Models [7.9051473654430655]
  Large language models (LLMs) are increasingly deployed in real-world applications that require careful balancing of multiple, often conflicting, objectives.<n>We propose a principled and computationally efficient algorithm designed explicitly for multi-objective alignment (MOA) in LLMs.<n>PAMA transforms multi-objective RLHF into a convex optimization with a closed-form solution, significantly enhancing scalability.
  arXiv  Detail & Related papers  (2025-08-11T08:54:14Z)
• Exact and Heuristic Algorithms for Constrained Biclustering [0.0]
  Biclustering, also known as co-clustering or two-way clustering, simultaneously partitions the rows and columns of a data matrix to reveal submatrices with coherent patterns.<n>We study constrained biclustering with pairwise constraints, namely must-link and cannot-link constraints, which specify whether objects should belong to the same or different biclusters.
  arXiv  Detail & Related papers  (2025-08-07T15:29:22Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [53.33473557562837]
  Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost. We propose a practical and scalable approach to solve this problem via mixture of experts (MoE) based model fusion. By ensembling the weights of specialized single-task models, the MoE module can effectively capture the trade-offs between multiple objectives.
  arXiv  Detail & Related papers  (2024-06-14T07:16:18Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [51.00436121587591]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours.<n>We focus on the case of linear utility functions parametrised by weight vectors w.<n>We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• BOtied: Multi-objective Bayesian optimization with tied multivariate ranks [33.414682601242006]
  In this paper, we show a natural connection between non-dominated solutions and the extreme quantile of the joint cumulative distribution function. Motivated by this link, we propose the Pareto-compliant CDF indicator and the associated acquisition function, BOtied. Our experiments on a variety of synthetic and real-world problems demonstrate that BOtied outperforms state-of-the-art MOBO acquisition functions.
  arXiv  Detail & Related papers  (2023-06-01T04:50:06Z)
• Late Fusion Multi-view Clustering via Global and Local Alignment Maximization [61.89218392703043]
  Multi-view clustering (MVC) optimally integrates complementary information from different views to improve clustering performance. Most of existing approaches directly fuse multiple pre-specified similarities to learn an optimal similarity matrix for clustering. We propose late fusion MVC via alignment to address these issues.
  arXiv  Detail & Related papers  (2022-08-02T01:49:31Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.