Abstract
High-dimensional Bayesian optimization (HDBO) seeks sample-efficient optimization when the number of variables is large relative to the evaluation budget. Recent LLM-based and agentic BO methods incorporate task knowledge and adapt search decisions during a run, but have primarily been evaluated on low- and moderate-dimensional problems. We ask whether this paradigm can transfer to the higher-dimensional regime. Our experiments show that these methods do not remain reliable in the high-dimensional regime, where the challenge is not only where to evaluate, but also which modeling assumption and search geometry to use when the objective's useful structure is unknown. We therefore introduce HERA, a Hypothesis- and Evidence-guided Research Agent that uses task context, optimization feedback, and structural diagnostics to revise search hypotheses, select and configure HDBO strategies, and determine their execution length. PRISM, its numerical optimization engine, generates and evaluates candidates sequentially within each search block, updating numerical models after each observation. HERA remains competitive with strong numerical HDBO baselines and outperforms the evaluated LLM-based and agentic methods on four metadata-free synthetic functions. Across eight real-world tasks, HERA achieves the best mean final objective among all evaluated systems on most benchmarks. Further analyses show that structural diagnostics change strategy use, metadata effects vary across tasks, and adaptive search blocks reduce inference cost.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Gao, Z. X., Xue, K., Tan, R. X., Chen, M., & Qian, C. (2026). Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search. https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search
MLA 9
Gao, Zhi-Xuan, et al. "Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search." https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search.
Chicago (author–date)
Gao, Zhi-Xuan, Ke Xue, Rong-Xi Tan, Ming Chen, and Chao Qian. 2026. "Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search." https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search.
Harvard
Gao, Z. X., Xue, K., Tan, R. X., Chen, M. and Qian, C. (2026) 'Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search', Available at: https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search.
Vancouver
Gao ZX, Xue K, Tan RX, Chen M, Qian C. Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search. https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search
IEEE
Z. X. Gao, K. Xue, R. X. Tan, M. Chen, and C. Qian, "Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search," https://omanscience.com/en/articles/agentic-high-dimensional-bayesian-optimization-with-hypothesis-and-evidence-guided-search.