LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation

TL;DR

LAPPI is an interactive system that leverages large language models to assist users in defining combinatorial optimization problems from vague preferences, improving solution relevance and user experience.

Contribution

The paper introduces LAPPI, a novel LLM-assisted interactive framework for preference-based problem instantiation in combinatorial optimization tasks.

Findings

LAPPI effectively captures user preferences in trip planning.

Generated solutions outperform conventional approaches.

System adapts to different use cases.

Abstract

Many real-world tasks, such as trip planning or meal planning, can be formulated as combinatorial optimization problems. However, using optimization solvers is difficult for end users because it requires problem instantiation: defining candidate items, assigning preference scores, and specifying constraints. We introduce LAPPI (LLM-Assisted Preference-based Problem Instantiation), an interactive approach that uses large language models (LLMs) to support users in this instantiation process. Through natural language conversations, the system helps users transform vague preferences into well-defined optimization problems. These instantiated problems are then passed to existing optimization solvers to generate solutions. In a user study on trip planning, our method successfully captured user preferences and generated feasible plans that outperformed both conventional and prompt-engineering approaches. We further demonstrate LAPPI's versatility by adapting it to an additional use case.