DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil Engineering

TL;DR

DrafterBench is a comprehensive open-source benchmark designed to evaluate large language models' ability to perform technical drawing revision tasks in civil engineering, assessing their understanding, reasoning, and adaptability.

Contribution

The paper introduces DrafterBench, the first specialized benchmark for LLMs in civil engineering tasks, with detailed evaluation metrics and a diverse set of real-world tasks.

Findings

LLMs demonstrate strong performance in structured data comprehension.

The benchmark reveals specific areas for improvement in instruction following.

Analysis provides insights into LLM capabilities and limitations in civil engineering contexts.

Abstract

Large Language Model (LLM) agents have shown great potential for solving real-world problems and promise to be a solution for tasks automation in industry. However, more benchmarks are needed to systematically evaluate automation agents from an industrial perspective, for example, in Civil Engineering. Therefore, we propose DrafterBench for the comprehensive evaluation of LLM agents in the context of technical drawing revision, a representation task in civil engineering. DrafterBench contains twelve types of tasks summarized from real-world drawing files, with 46 customized functions/tools and 1920 tasks in total. DrafterBench is an open-source benchmark to rigorously test AI agents' proficiency in interpreting intricate and long-context instructions, leveraging prior knowledge, and adapting to dynamic instruction quality via implicit policy awareness. The toolkit comprehensively assesses distinct capabilities in structured data comprehension, function execution, instruction following, and critical reasoning. DrafterBench offers detailed analysis of task accuracy and error statistics, aiming to provide deeper insight into agent capabilities and identify improvement targets for integrating LLMs in engineering applications. Our benchmark is available at https://github.com/Eason-Li-AIS/DrafterBench, with the test set hosted at https://huggingface.co/datasets/Eason666/DrafterBench.