cs.AINov 16, 2026

CivilBench: Benchmarking Vision-Language Models for Multimodal Information Integration in Civil Engineering

Authors: Dan Yuan, Yue Wen, Zhili He, Zhenkui Zhou, Shicen Liu, Ziqiang Zheng

Organizations: Faculty of Information Science and Electrical Engineering, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan · School of Civil Engineering, Sichuan University of Science & Engineering, Zigong 643000, China · Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, China · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China

Abstract

Artificial intelligence (AI), particularly large language models (LLMs) and vision-language models (VLMs), is increasingly applied in civil and structural engineering for disaster assessment, structural analysis, and engineering decision support. However, the extent to which current VLMs possess the reasoning capabilities required for reliable engineering judgments remains unclear. In this work, we introduce CivilBench, a comprehensive benchmark for evaluating VLMs in civil engineering and disaster-related scenarios. CivilBench covers three major task families: Sequential Reasoning, Image-based Structural Understanding, and Open-world Understanding, encompassing numerical reasoning, structural damage assessment, risk inference, causal analysis, and repair planning. The benchmark is constructed through a systematic pipeline of domain-specific data collection, engineering-oriented captioning, expert annotation, question design, and quality verification. Evaluation of representative state-of-the-art VLMs reveals substantial limitations in domain-specific reasoning, with Sequential Reasoning emerging as a major bottleneck, particularly when models must infer numerical relationships from sparse structured observations. Further experiments show that numerical priors and external knowledge can alleviate these limitations, although their effectiveness depends on the model's ability to reliably interpret and use the available evidence. CivilBench provides a capability-oriented testbed for identifying reasoning limitations and evaluating progress toward reliable AI-assisted engineering decision-making. The benchmark will be publicly available at https://huggingface.co/datasets/traceuryuan/CivilBench.

Figures & tables

Explore similar work

CardsList
  1. Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation

    Jun 9, 2026Syed Wasiq, Syed Mohamad Tawseeq, Yashwant Pravinrao Bangde +1VLM EvaluationVisual Question Answering

  2. MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence

    Aug 10, 2026Chenxu Du, Kang An, Tengyue Wang +8Multimodal ReasoningVisually Grounded Reasoning

  3. Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning

    Mar 20, 2026Hui Zhong, Yichun Gao, Luyan Liu +4Zero-Shot Referring Image SegmentationMultimodal Model Evaluation