用贝叶斯优化自动发现并优化新任务，提升科研流程效率。
Open-Ended Task Discovery via Bayesian Optimization
- 通过生成-选择-精炼循环动态生成新优化任务。
- 渐近收敛到最优任务，额外损失仅对数级。
- 适合科研探索、药物合成等开放式创新场景。
在科学工作流中应用贝叶斯优化时，任务本身的不确定性——即优化目标和评估方式——常被忽视，但会随证据积累而演变。本文提出生成-选择-精炼（GSR）框架，实现任务生成与优化的交替迭代。从用户提供的初始任务出发，GSR以粗到细的方式生成新任务，并通过任务获取函数调度优化过程。理论上，其渐近集中于最优任务，相对于单任务贝叶斯优化，仅引入对数级别的后悔代价。将GSR应用于新产品开发、化学合成放大、算法分析及专利再利用，结果表明其优于现有基于大模型的优化器。
原文摘要 · Abstract (English)
When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what to optimize and how to evaluate it -- which can evolve as evidence accumulates. We introduce Generate-Select-Refine (GSR), a open-ended BO framework that alternates between task generation and task optimization. Starting from a user-provided seed task, GSR generates new tasks in a coarse-to-fine manner while a task-acquisition function schedules optimization. Asymptotically, it concentrates evaluations on the best task, incurring only logarithmic regret overhead relative to single-task BO. We apply GSR to new product development, chemical synthesis scaling, algorithm analysis, and patent repurposing, where it outperforms existing LLM-based optimizers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。