Agentic Risk-Aware Set-Based Engineering Design

2026-04-17

AI Summary

This work proposes a large language model–driven multi-agent collaborative framework to address the challenges of vast parameter spaces, high uncertainty, and inefficient manual exploration in early-stage engineering design. By integrating set-based design with Conditional Value-at-Risk (CVaR), the framework enables risk-aware exploration of the design space, introducing CVaR into set-based design for the first time to automatically filter out high-failure-risk alternatives. Leveraging global sensitivity analysis and high-fidelity CFD simulations, multiple agents coordinate to generate a refined set of design candidates subject to rigorous risk assessment. Demonstrated on an airfoil aerodynamic design task, the approach significantly enhances decision-making efficiency and reliability for human experts operating under complex uncertainties.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a human-in-the-loop paradigm and demonstrated on the canonical problem of aerodynamic airfoil design, the framework employs a team of specialized agents: a Coding Assistant, a Design Agent, a Systems Engineering Agent, and an Analyst Agent - all coordinated by a human Manager. Integrated within a set-based design philosophy, the process begins with a collaborative phase where the Manager and Coding Assistant develop a suite of validated tools, after which the agents execute a structured workflow to systematically explore and prune a large set of initial design candidates. A key contribution of this work is the explicit integration of formal risk management, employing the Conditional Value-at-Risk (CVaR) as a quantitative metric to filter designs that exhibit a high probability of failing to meet performance requirements, specifically the target coefficient of lift. The framework automates labor-intensive initial exploration through a global sensitivity analysis conducted by the Analyst agent, which generates actionable heuristics to guide the other agents. The process culminates by presenting the human Manager with a curated final set of promising design candidates, augmented with high-fidelity Computational Fluid Dynamics (CFD) simulations. This approach effectively leverages AI to handle high-volume analytical tasks, thereby enhancing the decision-making capability of the human expert in selecting the final, risk-assessed design.

Problem

• engineering design
• uncertainty
• risk management
• design exploration
• parameter space

Innovation

• Multi-agent framework
• Set-based design
• Conditional Value-at-Risk (CVaR)
• Large Language Models (LLMs)
• Global sensitivity analysis