Management, Orchestration and Supervision of AI-agent COmmunities for reliable AI in software engineering

Informations projet

MOSAICO

N° de convention de subvention: 101189664

DOI

10.3030/101189664

Date de signature de la CE 12 Novembre 2024

Date de début 1 Janvier 2025

Date de fin 31 Decembre 2027

Financé au titre de

• Digital, Industry and Space

Coût total

Aucune donnée

Contribution de l’UE

€ 5 218 186,88

Coordonné par

INSTITUT MINES-TELECOM
France

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Publications

Conference proceedings (11)

Generate with CodeXHug: A Dataset to Enhance Model Cards with Code Usage Patterns

Auteurs: Stefano Palombo, Claudio Di Sipio, Juri Di Rocco, Davide Di Ruscio
Publié dans: Lecture Notes in Computer Science, Software Engineering and Advanced Applications, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-04207-1_22

When Retriever Meets Generator: A Joint Model for Code Comment Generation

Auteurs: Tien P. T. Le, Anh M. T. Bui, Huy N. D. Pham, Alessio Bucaioni, Phuong T. Nguyen
Publié dans: 19th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2025), 2025
Éditeur: IEEE
DOI: 10.48550/ARXIV.2507.12558

Towards Diagram-Based Data Model Generation with LLMs

Auteurs: Léna Bamouh, Thibault Béziers La Fosse, Massimo Tisi
Publié dans: Lecture Notes in Computer Science, Advances in Conceptual Modeling, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-032-08620-4_10

Towards Automated Governance: A DSL for Human-Agent Collaboration in Software Projects

Auteurs: Adem Ait, Gwendal Jouneaux, Javier Luis Cánovas Izquierdo, Jordi Cabot
Publié dans: 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026
Éditeur: IEEE
DOI: 10.1109/ASE63991.2025.00337

Bake Two Cakes with One Oven: RL for Defusing Popularity Bias and Cold-start in Third-Party Library Recommendations

Auteurs: Hoang Minh Vuong, Anh M. T. Bui, Phuong T. Nguyen, Davide Di Ruscio
Publié dans: Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering, 2025
Éditeur: ACM
DOI: 10.1145/3756681.3757043

Teamwork makes the dream work: LLMs-Based Agents for GitHub README.MD Summarization

Auteurs: Duc S. H. Nguyen, Bach G. Truong, Phuong T. Nguyen, Juri Di Rocco, Davide Di Ruscio
Publié dans: Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, 2025
Éditeur: ACM
DOI: 10.1145/3696630.3728511

Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy

Auteurs: Motunrayo Osatohanmen Ibiyo, Thinakone Louangdy, Phuong T. Nguyen, Claudio Di Sipio, Davide Di Ruscio
Publié dans: Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering, 2025
Éditeur: ACM
DOI: 10.1145/3756681.3757042

Simplicity by Obfuscation: Evaluating LLM-Driven Code Transformation with Semantic Elasticity

Auteurs: Lorenzo De Tomasi, Claudio Di Sipio, Antinisca Di Marco, Phuong T. Nguyen
Publié dans: Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering, 2025
Éditeur: ACM
DOI: 10.1145/3756681.3757041

Towards sustainability model cards

Auteurs: Gwendal Jouneaux, Jordi Cabot
Publié dans: SEAA 2025, 2025
Éditeur: arXiv
DOI: 10.48550/ARXIV.2507.19559

Larger Is Not Always Better: Leveraging Structured Code Diffs for Comment Inconsistency Detection

Auteurs: Phong Nguyen and Anh M. T. Bui and Phuong T. Nguyen
Publié dans: SANER 2026, 2025
Éditeur: arXiv.org
DOI: 10.48550/ARXIV.2512.19883

MOSAICO: Management, Orchestration and Supervision of AI-agent COmmunities for reliable AI in software engineering

Auteurs: Tisi, Massimo; Cabot, Jordi; Di Ruscio, Davide; Garcia-Dominguez, Antonio
Publié dans: Proceedings of the Research Projects Exhibition Papers Presented at the 37th International Conference on Advanced Information Systems Engineering (CAiSE 2025), 2025, ISSN 1613-0073
Éditeur: CEUR-WS

Peer reviewed articles (5)

Binary and multi-class classification of Self-Admitted Technical Debt: How far can we go?

Auteurs: Francesca Arcelli Fontana, Juri Di Rocco, Davide Di Ruscio, Amleto Di Salle, Phuong T. Nguyen
Publié dans: Information and Software Technology, Numéro 187, 2025, ISSN 0950-5849
Éditeur: Elsevier BV
DOI: 10.1016/J.INFSOF.2025.107862

Information and Software Technology

Auteurs: Arcelli Fontana, Francesca; Di Rocco, Juri; Di Ruscio, Davide; Di Salle, Amleto; Nguyen, Phuong
Publié dans: Information and Software Technology, Numéro Vol. 187, No. C, 2025, ISSN 0950-5849
Éditeur: Elsevier BV
DOI: 10.2139/SSRN.5209087

Detection of Technical Debt in Java Source Code

Auteurs: Nam Le Hai, Anh M. T. Bui, Phuong T. Nguyen, Davide Di Ruscio, Rick Kazman
Publié dans: ACM Transactions on Software Engineering and Methodology, 2026, ISSN 1049-331X
Éditeur: Association for Computing Machinery (ACM)
DOI: 10.1145/3801745

Many hands make light work: An LLM-based multi-agent system for detecting malicious PyPI packages

Auteurs: Muhammad Umar Zeshan, Motunrayo Ibiyo, Claudio Di Sipio, Phuong T. Nguyen, Davide Di Ruscio
Publié dans: Journal of Systems and Software, Numéro 236, 2026, ISSN 0164-1212
Éditeur: Elsevier BV
DOI: 10.1016/J.JSS.2026.112792

Automated summarization of software documents: an LLM-based multi-agent approach

Auteurs: Duc S. H. Nguyen, Minh T. Nguyen, Phuong T. Nguyen, Juri Di Rocco, Davide Di Ruscio
Publié dans: Automated Software Engineering, Numéro 33, 2026, ISSN 0928-8910
Éditeur: Springer Science and Business Media LLC
DOI: 10.1007/S10515-025-00588-4