Agentic Risk-Aware Set-Based Engineering Design

TL;DR

This paper presents a multi-agent, LLM-guided framework for early-stage engineering design that integrates risk management, set-based exploration, and human-in-the-loop decision-making, demonstrated on airfoil design.

Contribution

It introduces a novel multi-agent system that combines LLMs, formal risk metrics, and set-based design to automate and improve early engineering design processes.

Findings

Automated exploration of large design spaces with risk filtering.

Integration of CVaR for risk-aware design selection.

Enhanced decision support for human engineers in early design stages.

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.