analiza aiqbench
This research demonstrates how large language models can effectively integrate rich auxiliary data—such as expert notes and training curves—to enhance Bayesian Optimization beyond standard function evaluations. By applying these methods to hyperparameter tuning and a nuclear fusion task, the study shows consistent performance gains over existing approaches, highlighting a practical pathway for leveraging LLMs in complex scientific optimization workflows.
Bayesian Optimization with Rich Auxiliary Information via LLMs
arXiv:2609.19437v1 Announce Type: new Abstract: Bayesian Optimization (BO) is widely used for optimizing expensive black-box functions, yet many real-world optimization problems contain substantially richer information than function evaluations alone. Examples include training curves in hyperparameter optimization, expert notes and images in scientific experimentation, and prior knowledge about where optima may lie. We show that large language models (LLMs) can effectively leverage such rich auxiliary information to guide optimization. Motivated by these findings, we develop three methods for incorporating auxiliary information into BO using LLMs. Across hyperparameter optimization benchmarks and a real-world nuclear fusion optimization task, our methods consistently outperform both standard BO and existing LLM-based optimization approaches. Our results demonstrate the effectiveness of LLMs for leveraging rich auxiliary information in BO.
Abstract:Bayesian Optimization (BO) is widely used for optimizing expensive black-box functions, yet many real-world optimization problems contain substantially richer information than function evaluations alone. Examples include training curves in hyperparameter optimization, expert notes and images in scientific experimentation, and prior knowledge about where optima may lie. We show that large language models (LLMs) can effectively leverage such rich auxiliary information to guide optimization. Motivated by these findings, we develop three methods for incorporating auxiliary information into BO using LLMs. Across hyperparameter optimization benchmarks and a real-world nuclear fusion optimization task, our methods consistently outperform both standard BO and existing LLM-based optimization approaches. Our results demonstrate the effectiveness of LLMs for leveraging rich auxiliary information in BO.
Machine Learning (cs.LG)
arXiv:2609.19437 [cs.LG]
(or arXiv:2609.19437v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.19437 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 210 cuvinte
Subiecte conexe
Generalization and infinite width
LessWrong · 1 aug. 2026
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
arXiv · 17 iun. 2026
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
Reflections on unlearning and inoculation
LessWrong · 20 sept. 2026