DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li
Abstract
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.
BibTeX
@inproceedings{li-etal-2025-deepsolution,
title = "{D}eep{S}olution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking",
author = "Li, Zhuoqun and
Yu, Haiyang and
Chen, Xuanang and
Lin, Hongyu and
Lu, Yaojie and
Huang, Fei and
Han, Xianpei and
Li, Yongbin and
Sun, Le",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.220/",
doi = "10.18653/v1/2025.acl-long.220",
pages = "4380--4396",
ISBN = "979-8-89176-251-0"
}