Abstract:Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key challenge: the inherently multi-faceted nature of prompt performance, which cannot be captured by a single metric. To fill this gap, we study the multi-objective prompt selection problem under two practical settings: Pareto prompt set recovery and best feasible prompt identification. Casting the problem into the pure-exploration bandits framework, we adapt provably efficient algorithms from multi-objective bandits and further introduce a novel design for best feasible arm identification in structured bandits, with theoretical guarantees on the identification error in the linear case. Extensive experiments across multiple LLMs show that the bandit-based approaches yield significant improvements over baselines, establishing a principled and efficient framework for multi-objective prompt optimization.
| Comments: | Published as a conference paper at ICLR 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.14553 [cs.LG] |
| (or arXiv:2605.14553v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14553 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Donghao Li [view email]
[v1]
Thu, 14 May 2026 08:31:17 UTC (1,054 KB)