logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

AgentArcEval: An architecture evaluation method for foundation model based agents

delete2025-10-17
delete0
PRE
AI
Q
Qinghua Lu *
D
Dehai Zhao
Y
Yue Liu
H
Hao Zhang
L
Liming Zhu
X
Xiwei Xu
A
Angela Shi
T
Tristan Tan
R
Rick Kazman
DOI：10.1016/j.jss.2025.112656delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We propose a novel agent architecture evaluation method for FM-based agent architecture and its evaluation. • We present a catalogue of agent-specific general scenarios for generating concrete scenarios to design and evaluate agent architecture. • We demonstrate the usefulness of AgentArcEval and the catalogue through a real-world case study.

Journal

Journal of Systems and Software cover
Journal of Systems and Software
IF:
4.1
Papers:
5.4K
Citations:
8.4K

Organization

D
data61, csiro
Scholars:
7
Papers: 2
Citations: 0
U
University of Hawaii
Scholars:
164
Papers: 122
Citations: 79
E
empathetic ai
Scholars:
2
Papers: 1
Citations: 0
researcher View more organizations