DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916638203314176 |
|---|---|
| author | Li, Zhuoqun Yu, Haiyang Chen, Xuanang Lin, Hongyu Lu, Yaojie Huang, Fei Han, Xianpei Li, Yongbin Sun, Le |
| author_facet | Li, Zhuoqun Yu, Haiyang Chen, Xuanang Lin, Hongyu Lu, Yaojie Huang, Fei Han, Xianpei Li, Yongbin Sun, Le |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20730 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking Li, Zhuoqun Yu, Haiyang Chen, Xuanang Lin, Hongyu Lu, Yaojie Huang, Fei Han, Xianpei Li, Yongbin Sun, Le Artificial Intelligence Computation and Language 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. |
| title | DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.20730 |