Institution profile

Abo Akademi University

Academic institutioneurope · fi
Official website
Research library14linked papers
Opportunities0open roles
Selected work

Representative Papers

Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report

Aug 12, 2026

This study addresses the challenges developers face when building large language model–based multi-agent systems, particularly in framework selection, agent role design, and coordination mechanisms. From a developer-centric perspective, the work presents the first systematic evaluation of prominent open-source multi-agent frameworks through a mixed-methods approach, combining quantitative analysis of documentation and functional capabilities with a qualitative README summarization task experiment evaluated using ROUGE metrics. The authors propose an integrated assessment framework encompassing functional coverage, documentation quality, and practical efficacy. Findings reveal that while existing frameworks support core components, they generally lack advanced features—such as agent telemetry—and exhibit no statistically significant performance differences in the summarization task. The study provides practitioners with an evidence-based framework selection guide, a checklist of key development challenges, and empirical insights to inform real-world deployment decisions.

0 citationsRead paper

Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning

Jun 30, 2026

This work addresses the challenge of learning sparse models with strong generalization and accurate structural recovery in federated learning settings characterized by data sparsity, heterogeneity, and partial client participation. The authors propose a novel approach based on a probabilistic gating mechanism, which—by introducing entropy regularization into federated learning for the first time—preserves uncertainty in the sparse structure and prevents premature convergence to suboptimal support sets. Integrating L0 constraints with federated optimization, the method consistently outperforms baseline strategies such as Fed-IHT and post-hoc pruning of FedAvg across both synthetic and real-world datasets, achieving significant improvements in both test performance and accuracy of recovered sparse structures.

0 citationsRead paper
Recent publications

Latest Papers

Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report

Aug 12, 2026

This study addresses the challenges developers face when building large language model–based multi-agent systems, particularly in framework selection, agent role design, and coordination mechanisms. From a developer-centric perspective, the work presents the first systematic evaluation of prominent open-source multi-agent frameworks through a mixed-methods approach, combining quantitative analysis of documentation and functional capabilities with a qualitative README summarization task experiment evaluated using ROUGE metrics. The authors propose an integrated assessment framework encompassing functional coverage, documentation quality, and practical efficacy. Findings reveal that while existing frameworks support core components, they generally lack advanced features—such as agent telemetry—and exhibit no statistically significant performance differences in the summarization task. The study provides practitioners with an evidence-based framework selection guide, a checklist of key development challenges, and empirical insights to inform real-world deployment decisions.

0 citationsRead paper

Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning

Jun 30, 2026

This work addresses the challenge of learning sparse models with strong generalization and accurate structural recovery in federated learning settings characterized by data sparsity, heterogeneity, and partial client participation. The authors propose a novel approach based on a probabilistic gating mechanism, which—by introducing entropy regularization into federated learning for the first time—preserves uncertainty in the sparse structure and prevents premature convergence to suboptimal support sets. Integrating L0 constraints with federated optimization, the method consistently outperforms baseline strategies such as Fed-IHT and post-hoc pruning of FedAvg across both synthetic and real-world datasets, achieving significant improvements in both test performance and accuracy of recovered sparse structures.

0 citationsRead paper