Towards an Approach for Specifying Intelligent Systems Involving Foundation Model Based Agents

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Araújo, Julia, Marina, Araujo, Carvalho Boaro, Jose Matheus, Kalinowski, Marcos
Format: Recurso digital
Published: Zenodo 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902261296267264
author Araújo, Julia
Marina, Araujo
Carvalho Boaro, Jose Matheus
Kalinowski, Marcos
author_facet Araújo, Julia
Marina, Araujo
Carvalho Boaro, Jose Matheus
Kalinowski, Marcos
contents <p>The rise of foundation-model-based agents has introduced a new generation of intelligent systems capable of autonomous reasoning, reflection, and coordination. However, their specification remains challenging due to emergent behaviors and dynamic, probabilistic interactions that exceed the assumptions of traditional software and requirements engineering approaches. This short paper presents the vision of PerSpecAgents, a perspective-based approach designed to support the specification of intelligent systems involving such agents. The solution proposal extends an ML-enabled system specification approach by incorporating agent-oriented concerns, such as autonomy, reasoning loops, reflection mechanisms, memory management, and ethical guardrails. An initial academic validation with graduate-level participants allowed refinements and provided a preliminary indication of PerSpecAgents' clarity, completeness, and usefulness. These findings strengthen our confidence in the approach's potential to support the specification of intelligent systems built upon foundation models.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17418130
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Towards an Approach for Specifying Intelligent Systems Involving Foundation Model Based Agents
Araújo, Julia
Marina, Araujo
Carvalho Boaro, Jose Matheus
Kalinowski, Marcos
Requirements Engineering
Intelligent Systems
Agents
<p>The rise of foundation-model-based agents has introduced a new generation of intelligent systems capable of autonomous reasoning, reflection, and coordination. However, their specification remains challenging due to emergent behaviors and dynamic, probabilistic interactions that exceed the assumptions of traditional software and requirements engineering approaches. This short paper presents the vision of PerSpecAgents, a perspective-based approach designed to support the specification of intelligent systems involving such agents. The solution proposal extends an ML-enabled system specification approach by incorporating agent-oriented concerns, such as autonomy, reasoning loops, reflection mechanisms, memory management, and ethical guardrails. An initial academic validation with graduate-level participants allowed refinements and provided a preliminary indication of PerSpecAgents' clarity, completeness, and usefulness. These findings strengthen our confidence in the approach's potential to support the specification of intelligent systems built upon foundation models.</p>
title Towards an Approach for Specifying Intelligent Systems Involving Foundation Model Based Agents
topic Requirements Engineering
Intelligent Systems
Agents
url https://doi.org/10.5281/zenodo.17418130