DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
This addresses the gap in retrieval-augmented generation for complex engineering solution design, which is incremental as it builds on existing RAG methods with a new benchmark and system.
The paper tackles the problem of designing complex engineering solutions with multiple constraints by introducing a new benchmark called SolutionBench and proposing a novel system called SolutionRAG that uses tree-based exploration and bi-point thinking. The system achieves state-of-the-art performance on SolutionBench, demonstrating its potential to enhance automation and reliability in real-world engineering applications.
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.