arXiv subjects

Shaoyi Yang

Publications and source records attributed to Shaoyi Yang.

3 recordsLinked to original sources

arXiv2026

From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design

Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31.1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

cs.AI↗

arXiv2025

Chain of Draft for Software Engineering: Challenges in Applying Concise Reasoning to Code Tasks

Large language models (LLMs) have become vital tools for software development, but they often require verbose intermediate reasoning for complex code tasks, leading to high latency and costs. This research extends the Chain of Draft (CoD) method to software engineering, designing and evaluating multiple CoD variants tailored for code tasks. Through comprehensive experiments on all 300 samples from the SWE-bench benchmark, we found that all CoD variants used significantly fewer tokens than Chain of Thought (CoT), with Baseline CoD being most efficient at 55.4% of CoT's tokens. While this represents substantial efficiency gains - translating to approximately 45% reduction in processing time and API costs - it differs from the extreme 7.6% reported in the original CoD paper for mathematical reasoning. This difference stems from the inherent complexity and context-dependency of software tasks, which require more detailed reasoning to maintain solution quality. Our multi-dimensional quality assessment revealed that CoD variants maintain over 90% of CoT's code quality across key metrics including correctness, compatibility, and maintainability, making them practical alternatives for real-world development scenarios where efficiency matters. This research demonstrates how domain-specific characteristics influence prompting strategy effectiveness and provides a framework for balancing efficiency with solution quality in software engineering applications. Our findings offer practical guidance for optimizing LLM-based development workflows through appropriate prompting strategy selection based on project requirements.

cs.SE↗

arXiv2023

A Novel Perspective Process Simulation Framework Based on Automatic Differentiation

Thermodynamic and flash equilibrium calculations are the cornerstones of simulation process calculations. The iterative approach, a widely used nonlinear problem-solving technique, relies on derivative calculations throughout the procedure that directly affect the stability and effectiveness of the solution. In this study, we use state-of-the-art automatic differentiation frameworks for thermodynamic calculations to obtain precise derivatives without altering the logic of the algorithm. This contrasts with traditional numerical differentiation algorithms and significantly improves the convergence and computational efficiency of process simulations in contrast to numerical differentiation algorithms. Standard chemical phase equilibrium calculations such as PT, PV, and PH flash are used to evaluate an automated differentiation approach with respect to numerical stability and iteration counts. It is used to evaluate the iteration count. The results of the experiment showed that the automatic differentiation method has a more uniform gradient distribution and requires fewer convergence iterations. The experimental results show that the system shows that the process is more uniform. The gradient distribution and computational convergence curves help to highlight the improvements provided by automatic differentiation. In addition, this method shows greater generalizability and can be used more easily in the calculation of various other chemical simulation modules.

cs.CE↗