Modular construction, which involves unit production in factories and on-site work, has benefits such as low cost, high quality, and short duration, resulting from the controlled factory environment utilized. An efficient tower crane lifting plan ensures successful high-rise modular project completion. For improved efficiency, the lifting plan should minimize the reaching distance of the tower crane, because this distance directly affects the tower crane capacity, which is directly related to crane operation cost. In situations where units are lifted from trailers, the trailer-to-tower crane distance can have a significant impact on the tower crane operation efficiency. However, optimization of this distance to improve efficiency has not been sufficiently considered. This research proposes a genetic algorithm optimization model that suggests optimized tower crane and trailer locations. The case study results show that through the proposed model, the project manager can reflect the optimal location selection and optimal tower crane selection options with minimal cost.

This preliminary case study examines EXAONE 4.0 1.2B, an on-device large language model (LLM), in building environmental engineering, using ChatGPT-4o as a high-capability cloud reference rather than a size-matched competitor. Ten Korean-language items were evaluated: four multiple-choice, three single-step calculations, and three short-answer questions covering indoor environmental quality, energy, and post-occupancy evaluation. The same simple prompt condition was applied to both models, with no model-specific prompt optimization; therefore, the results represent one standardized condition rather than each model’s maximum performance. Both models answered all seven objective items correctly, although EXAONE showed terminology confusion in its reasoning on a thermal-environment item. Five doctoral-level experts rated the short-answer responses for accuracy, completeness, and logical consistency. Mean scores were 4.18 for ChatGPT-4o and 2.98 for EXAONE. Fleiss’ kappa was 0.020 and 0.044, while free-marginal kappa was 0.333 and 0.222, respectively; the latter values indicate fair, not moderate, agreement, so absolute expert scores require cautious interpretation. Qualitatively, ChatGPT-4o more consistently organized responses around concepts and scope, whereas EXAONE tended to provide specific technical, operational, and Korean-regulatory content but occasionally omitted canonical elements or added unsupported detail. Because the item pool is small and only one on-device model was tested, the findings are exploratory and cannot be generalized to building environmental engineering as a whole or to on-device LLMs as a class. The results support further investigation of on-device LLMs as supervised offline assistants where connectivity or external data transmission is constrained, but not as unsupervised tools for engineering calculation or compliance decisions.