[2603.28959] Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization

Computer Science > Machine Learning arXiv:2603.28959 (cs) [Submitted on 30 Mar 2026] Title:Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization Authors:Andrea Carbonati, Mohammadsina Almasi, Hadis Anahideh View a PDF of the paper titled Multi-Agent LLMs for Adaptive Acquisition in Bayesian Optimization, by Andrea Carbonati and 2 other authors View PDF HTML (experimental) Abstract:The exploration-exploitation trade-off is central to sequential decision-making and black-box optimization, yet how Large Language Models (LLMs) reason about and manage this trade-off remains poorly understood. Unlike Bayesian Optimization, where exploration and exploitation are explicitly encoded through acquisition functions, LLM-based optimization relies on implicit, prompt-based reasoning over historical evaluations, making search behavior difficult to analyze or control. In this work, we present a metric-level study of LLM-mediated search policy learning, studying how LLMs construct and adapt exploration-exploitation strategies under multiple operational definitions of exploration, including informativeness, diversity, and representativeness. We show that single-agent LLM approaches, which jointly perform strategy selection and candidate generation within a single prompt, suffer from cognitive overload, leading to unstable search dynamics and premature convergence. To address this limitation, we propose a multi-agent framework that decomposes exploration-exploitation control int...