arXiv cs.CL· Yutaro Yamada, Kei Hiroshima, Nozomu Yoshinari, Kento Uchida, Shinichi Shirakawa·· 2 天前AI 评分31
BBOWP-Bench:评估 LLM 在黑盒优化文字题上的表现
BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
AI 导读
研究者提出 BBOWP-Bench,用于评估 LLM 能否从自然语言描述中同时推断黑盒优化问题的搜索空间与优化算法。每个实例包含问题描述、可执行评估环境和人工设计的参考方案,覆盖多个黑盒优化领域。测试显示当前 LLM 会随评估预算调整优化器选择,但在问题描述信息不足或搜索空间高度特定时,识别关键变量与平衡变量范围仍有困难。
正文 · 原文
Abstract:Formulating an optimization problem strongly affects final solution quality, yet good formulations usually require substantial expertise. Recent studies have explored automatically deriving optimization problems from natural-language descriptions, but existing benchmarks focus on settings where objectives and constraints can be written explicitly as mathematical expressions. Many practically important problems are naturally treated as black-box optimization (BBO) problems, in which only objective values are observable, and the functional form is unavailable. In BBO, search space design (as part of problem formulation) and optimization algorithm selection are crucial for problem-solving. Automating these processes with large language models (LLMs) remains challenging. We introduce Black-Box Optimization Word Problems (BBOWP), a novel problem setting in which a system must infer both a search space and an optimization algorithm from a natural-language description of a black-box optimization task. To support research on this setting, we establish the BBOWP Benchmark Suite (BBOWP-Bench), a dataset and evaluation framework for BBOWP. Each instance combines a natural-language problem description, an executable evaluation environment, and a human-designed reference formulation, allowing evaluation of both search-space design and algorithm selection. Using this benchmark, we evaluate LLMs on the joint formulation of search spaces and optimizers from natural-language descriptions across multiple BBO domains. We show that current LLMs vary their optimizer choice with the evaluation budget, though they sometimes struggle with search space design, particularly in identifying important variables and balancing their ranges when the problem description is less informative or the search space is highly problem-specific. Our code and dataset are available at this https URL.
| Comments: | Accepted to NeurIPS 2026 (Evaluations & Datasets Track) |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) |
| Cite as: | arXiv:2608.02612 [cs.CL] |
| (or arXiv:2608.02612v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02612 arXiv-issued DOI via DataCite |
Submission history
From: Yutaro Yamada [view email]
[v1]
Wed, 20 May 2026 08:11:23 UTC (812 KB)
[v2]
Fri, 13 Nov 2026 05:59:33 UTC (826 KB)
来源:arXiv cs.CL · arxiv.org