Designing solutions for complex engineering challenges is crucial in human production activities. However, previous research in the retrieval-augmented generation (RAG) field has not sufficiently addressed tasks related to the design of complex engineering solutions. To fill this gap, we introduce a new benchmark, SolutionBench, to evaluate a system's ability to generate complete and feasible solutions for engineering problems with multiple complex constraints. To further advance the design of complex engineering solutions, we propose a novel system, SolutionRAG, that leverages the tree-based exploration and bi-point thinking mechanism to generate reliable solutions. Extensive experimental results demonstrate that SolutionRAG achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications.
View on arXiv@article{li2025_2502.20730,
title={ DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking },
author={ Zhuoqun Li and Haiyang Yu and Xuanang Chen and Hongyu Lin and Yaojie Lu and Fei Huang and Xianpei Han and Yongbin Li and Le Sun },
journal={arXiv preprint arXiv:2502.20730},
year={ 2025 }
}