On the Evaluation of Engineering Artificial General Intelligence

TL;DR

This paper proposes an extensible framework grounded in Bloom's taxonomy for evaluating engineering AGI agents across diverse tasks, including design and structured artifact assessment, to advance AI benchmarking in engineering.

Contribution

It introduces a novel evaluation framework tailored for engineering AGI, integrating Bloom's taxonomy with customizable, multi-modal assessment capabilities.

Findings

Developed a comprehensive taxonomy of evaluation questions.

Proposed a pluggable framework for diverse response types.

Outlined an automatable procedure for context-specific benchmarking.

Abstract

We discuss the challenges and propose a framework for evaluating engineering artificial general intelligence (eAGI) agents. We consider eAGI as a specialization of artificial general intelligence (AGI), deemed capable of addressing a broad range of problems in the engineering of physical systems and associated controllers. We exclude software engineering for a tractable scoping of eAGI and expect dedicated software engineering AI agents to address the software implementation challenges. Similar to human engineers, eAGI agents should possess a unique blend of background knowledge (recall and retrieve) of facts and methods, demonstrate familiarity with tools and processes, exhibit deep understanding of industrial components and well-known design families, and be able to engage in creative problem solving (analyze and synthesize), transferring ideas acquired in one context to another. Given this broad mandate, evaluating and qualifying the performance of eAGI agents is a challenge in itself and, arguably, a critical enabler to developing eAGI agents. In this paper, we address this challenge by proposing an extensible evaluation framework that specializes and grounds Bloom's taxonomy - a framework for evaluating human learning that has also been recently used for evaluating LLMs - in an engineering design context. Our proposed framework advances the state of the art in benchmarking and evaluation of AI agents in terms of the following: (a) developing a rich taxonomy of evaluation questions spanning from methodological knowledge to real-world design problems; (b) motivating a pluggable evaluation framework that can evaluate not only textual responses but also evaluate structured design artifacts such as CAD models and SysML models; and (c) outlining an automatable procedure to customize the evaluation benchmark to different engineering contexts.