AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Qinghua, Zhao, Dehai, Liu, Yue, Zhang, Hao, Zhu, Liming, Xu, Xiwei, Shi, Angela, Tan, Tristan, Kazman, Rick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909867125506048
author Lu, Qinghua
Zhao, Dehai
Liu, Yue
Zhang, Hao
Zhu, Liming
Xu, Xiwei
Shi, Angela
Tan, Tristan
Kazman, Rick
author_facet Lu, Qinghua
Zhao, Dehai
Liu, Yue
Zhang, Hao
Zhu, Liming
Xu, Xiwei
Shi, Angela
Tan, Tristan
Kazman, Rick
contents The emergence of foundation models (FMs) has enabled the development of highly capable and autonomous agents, unlocking new application opportunities across a wide range of domains. Evaluating the architecture of agents is particularly important as the architectural decisions significantly impact the quality attributes of agents given their unique characteristics, including compound architecture, autonomous and non-deterministic behaviour, and continuous evolution. However, these traditional methods fall short in addressing the evaluation needs of agent architecture due to the unique characteristics of these agents. Therefore, in this paper, we present AgentArcEval, a novel agent architecture evaluation method designed specially to address the complexities of FM-based agent architecture and its evaluation. Moreover, we present a catalogue of agent-specific general scenarios, which serves as a guide for generating concrete scenarios to design and evaluate the agent architecture. We demonstrate the usefulness of AgentArcEval and the catalogue through a case study on the architecture evaluation of a real-world tax copilot, named Luna.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents
Lu, Qinghua
Zhao, Dehai
Liu, Yue
Zhang, Hao
Zhu, Liming
Xu, Xiwei
Shi, Angela
Tan, Tristan
Kazman, Rick
Software Engineering
Artificial Intelligence
The emergence of foundation models (FMs) has enabled the development of highly capable and autonomous agents, unlocking new application opportunities across a wide range of domains. Evaluating the architecture of agents is particularly important as the architectural decisions significantly impact the quality attributes of agents given their unique characteristics, including compound architecture, autonomous and non-deterministic behaviour, and continuous evolution. However, these traditional methods fall short in addressing the evaluation needs of agent architecture due to the unique characteristics of these agents. Therefore, in this paper, we present AgentArcEval, a novel agent architecture evaluation method designed specially to address the complexities of FM-based agent architecture and its evaluation. Moreover, we present a catalogue of agent-specific general scenarios, which serves as a guide for generating concrete scenarios to design and evaluate the agent architecture. We demonstrate the usefulness of AgentArcEval and the catalogue through a case study on the architecture evaluation of a real-world tax copilot, named Luna.
title AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2510.21031