Large Language Models for Multi-Facility Location Mechanism Design
This addresses the problem of designing transparent and efficient mechanisms for multi-facility location, which is important for applications requiring strategyproofness and interpretability, though it is incremental by building on prior deep learning approaches.
The paper tackled the challenge of designing strategyproof mechanisms for multi-facility location by introducing LLMMech, which uses large language models in an evolutionary framework to generate interpretable and hyperparameter-free mechanisms; the results show that these mechanisms outperform existing baselines and deep learning models, with strong generalizability to out-of-distribution preferences and larger instances.
Designing strategyproof mechanisms for multi-facility location that optimize social costs based on agent preferences had been challenging due to the extensive domain knowledge required and poor worst-case guarantees. Recently, deep learning models have been proposed as alternatives. However, these models require some domain knowledge and extensive hyperparameter tuning as well as lacking interpretability, which is crucial in practice when transparency of the learned mechanisms is mandatory. In this paper, we introduce a novel approach, named LLMMech, that addresses these limitations by incorporating large language models (LLMs) into an evolutionary framework for generating interpretable, hyperparameter-free, empirically strategyproof, and nearly optimal mechanisms. Our experimental results, evaluated on various problem settings where the social cost is arbitrarily weighted across agents and the agent preferences may not be uniformly distributed, demonstrate that the LLM-generated mechanisms generally outperform existing handcrafted baselines and deep learning models. Furthermore, the mechanisms exhibit impressive generalizability to out-of-distribution agent preferences and to larger instances with more agents.