DASH: Decoupled Adaptive Surrogate - Acquisition Harness for Automated Bayesian Optimization

2026-08-01

AI Summary

This work addresses the limitations of traditional automated Bayesian optimization, where the coupled selection of surrogate models and acquisition functions often leads to component mismatch and poor adaptability to dynamic task requirements and optimization stages. To overcome this, the authors propose DASH, a novel framework that decouples and adaptively selects both components for the first time. DASH dynamically chooses surrogate models based on predictive reliability, uncertainty calibration, and ranking consistency, while a two-stage acquisition controller allocates evaluation budgets and leverages large language models (LLMs) for decision-making. Domain knowledge is further integrated through knowledge-guided warm starts and structured memory. Evaluated on four chemical optimization tasks, DASH achieves a 12.51% trajectory-level speedup and a 5.00% improvement in final performance over the best AutoBO baseline, demonstrating robustness across different LLM backbones.

Abstract

Bayesian optimization (BO) relies on a surrogate model and an acquisition function, yet the most suitable choices vary across tasks and optimization stages. Automated Bayesian optimization (AutoBO) addresses this variability by adapting BO components online. However, existing AutoBO methods either adapt one component, leaving the other mismatched and creating a bottleneck, or jointly select surrogate--acquisition pairs under a shared criterion, overlooking their distinct roles: surrogate selection depends on predictive reliability, whereas acquisition adaptation should respond to campaign context.In this paper, we propose DASH, a Decoupled Adaptive Surrogate--Acquisition Harness for large-language- model (LLM)-enhanced AutoBO. DASH selects surrogates by predictive reliability, uncertainty calibration, and ranking consistency; its two-stage acquisition controller periodically reallocates quotas across acquisition functions, builds a BO shortlist accordingly, and delegates final selection to an LLM. DASH also incorporates an integrated harness, consisting of knowledge-guided warm start and structured memory, to ground optimization in domain knowledge and accumulated feedback. Across four chemical optimization tasks, DASH outperforms the best AutoBO baseline by 12.51% in trajectory-level Acceleration Factor and 5.00% in endpoint Enhancement Factor. Results remain strong across LLM backbones, and ablations verify the complementary contributions of all components. Full-table and behavioral contamination checks find no detectable evidence that direct benchmark memorization or source-cell leakage explains these gains.

Problem

• Bayesian optimization
• surrogate model
• acquisition function
• automated Bayesian optimization
• component adaptation

Innovation

• Decoupled Adaptation
• Surrogate Model Selection
• Acquisition Function Allocation
• LLM-enhanced Bayesian Optimization
• Structured Memory