Cooperative Design Optimization through Natural Language Interaction
Ryogo Niwa, Shigeo Yoshida, Yuki Koyama, Yoshitaka Ushiku
Abstract
Figure 1: Concept of cooperative design optimization through natural language interaction. The user interface designer iteratively conducts user tests to discover the best design parameters (right side). During this process, the designer cooperates with our system, a Bayesian optimization (BO) system extended with a large language model (LLM), to decide the condition to test next (left side). The cooperation is done through natural language, offering the opportunity for flexible and cognitively easy intervention in the optimization process.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 463dc2cd-7ed0-4175-b88a-53fbbe07f5afCited by top-tier papers1
Ask how each one uses itBuilds on12
- Large Language Models as OptimizersChengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu et al.ICLR 2024 · 817 citations
- BoTorch: A Framework for Efficient Monte-Carlo Bayesian OptimizationMaximilian Balandat, Brian Karrer, Daniel R. Jiang, Samuel Daulton et al.NeurIPS 2020 · 686 citations
- Unexpected Improvements to Expected Improvement for Bayesian OptimizationSebastian Ament, Samuel Daulton, David Eriksson, Maximilian Balandat et al.NeurIPS 2023 · 280 citations
- Large Language Models to Enhance Bayesian OptimizationTennison Liu, Nicolás Astorga, Nabeel Seedat, Mihaela van der SchaarICLR 2024 · 143 citations
- Investigating Positive and Negative Qualities of Human-in-the-Loop Optimization for Designing Interaction TechniquesLiwei Chan, Yi-Chi Liao, George B. Mo, John J. Dudley et al.CHI 2022 · 94 citations
Related papers
- LILO: Bayesian Optimization with Natural Language FeedbackKatarzyna Kobalczyk, Zhiyuan Lin, Benjamin Letham, Zhuokai Zhao et al.ICML 2026 · 2 citations
- BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental DesignDeepro Choudhury, Sinead Williamson, Adam Golinski, Ning Miao et al.ICLR 2026 · 24 citations
- CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter OptimizationBeicheng Xu, Keyao Ding, Wei Liu, Yupeng Lu et al.KDD 2026
- Multi-Agent Design: Optimizing Agents with Better Prompts and TopologiesHan Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi et al.ICLR 2026 · 127 citations
- DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented InterfacesYuan Xu, Shaowen Xiang, Yizhi Song, Ruoting Sun et al.CHI 2026 · 2 citations
