DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

• URL: http://arxiv.org/abs/2502.20730v1
• Date: Fri, 28 Feb 2025 05:23:10 GMT
• Title: DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
• Authors: Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun,
• Abstract summary: We introduce a new benchmark, SolutionBench, to evaluate a system's ability to generate complete and feasible solutions for engineering problems.<n>We propose a novel system, SolutionRAG, that leverages the tree-based exploration and bi-point thinking mechanism to generate reliable solutions.
• Score: 96.92117129897505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Towards Resilient and Sustainable Global Industrial Systems: An Evolutionary-Based Approach [0.14660435286994572]
  This paper presents a new complex optimization problem in the field of automatic design of industrial systems. It aims at finding solutions that minimize CO2 emissions, transportation time, and costs. The proposed methodology can be applied to any industry case with complex manufacturing and supply chain challenges.
  arXiv  Detail & Related papers  (2025-03-05T22:10:32Z)
• PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving [89.60370366013142]
  We propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents.<n>Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms.
  arXiv  Detail & Related papers  (2025-02-22T06:21:56Z)
• AIDE: AI-Driven Exploration in the Space of Code [6.401493599308353]
  We introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs)<n>AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions.<n>By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance.
  arXiv  Detail & Related papers  (2025-02-18T18:57:21Z)
• Creating Automated Quantum-Assisted Solutions for Optimization Problems [0.0]
  We propose the QuaST decision tree, a framework that allows to explore, automate and evaluate solution paths. Our setup is modular, highly structured and flexible enough to include any kind of preparation, pre-processing and post-processing steps.
  arXiv  Detail & Related papers  (2024-09-30T16:59:14Z)
• Dynamic Decision Making in Engineering System Design: A Deep Q-Learning Approach [1.3812010983144802]
  We present a framework proposing the use of the Deep Q-learning algorithm to optimize the design of engineering systems. The goal is to find policies that maximize the output of a simulation model given multiple sources of uncertainties. We demonstrate the effectiveness of our proposed framework by solving two engineering system design problems in the presence of multiple uncertainties.
  arXiv  Detail & Related papers  (2023-12-28T06:11:34Z)
• Efficient lifting of symmetry breaking constraints for complex combinatorial problems [9.156939957189502]
  This work extends the learning framework and implementation of a model-based approach for Answer Set Programming. In particular, we incorporate a new conflict analysis algorithm in the Inductive Logic Programming system ILASP.
  arXiv  Detail & Related papers  (2022-05-14T20:42:13Z)
• Machine Learning Methods in Solving the Boolean Satisfiability Problem [72.21206588430645]
  The paper reviews the recent literature on solving the Boolean satisfiability problem (SAT) with machine learning techniques. We examine the evolving ML-SAT solvers from naive classifiers with handcrafted features to the emerging end-to-end SAT solvers such as NeuroSAT.
  arXiv  Detail & Related papers  (2022-03-02T05:14:12Z)
• Simultaneous Navigation and Construction Benchmarking Environments [73.0706832393065]
  We need intelligent robots for mobile construction, the process of navigating in an environment and modifying its structure according to a geometric design. In this task, a major robot vision and learning challenge is how to exactly achieve the design without GPS. We benchmark the performance of a handcrafted policy with basic localization and planning, and state-of-the-art deep reinforcement learning methods.
  arXiv  Detail & Related papers  (2021-03-31T00:05:54Z)
• SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning [0.0]
  This paper presents the proof of concept for SeaPearl, a new constraint programming solver implemented in Julia. SeaPearl supports machine learning routines in order to learn branching decisions using reinforcement learning. Although not yet competitive with industrial solvers, SeaPearl aims to provide a flexible and open-source framework.
  arXiv  Detail & Related papers  (2021-02-18T07:34:38Z)
• Learning What to Defer for Maximum Independent Sets [84.00112106334655]
  We propose a novel DRL scheme, coined learning what to defer (LwD), where the agent adaptively shrinks or stretch the number of stages by learning to distribute the element-wise decisions of the solution at each stage. We apply the proposed framework to the maximum independent set (MIS) problem, and demonstrate its significant improvement over the current state-of-the-art DRL scheme.
  arXiv  Detail & Related papers  (2020-06-17T02:19:31Z)
• MineReduce: an approach based on data mining for problem size reduction [58.720142291102135]
  This paper presents an approach named MineReduce, which uses mined patterns to perform problem size reduction. We present an application of MineReduce to improve a for the heterogeneous fleet vehicle routing problem.
  arXiv  Detail & Related papers  (2020-05-15T08:49:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.