LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation
This addresses the problem of making combinatorial optimization accessible to end users in tasks like trip planning, though it is incremental as it builds on existing solvers and LLMs.
The paper tackled the difficulty of using optimization solvers for end users by introducing LAPPI, an interactive approach that uses LLMs to transform vague preferences into well-defined optimization problems through natural language conversations, resulting in a user study where it successfully captured preferences and generated feasible plans that outperformed conventional and prompt-engineering approaches.
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.