Hoang D. Nguyen

Hoang D. Nguyen

Auto-generated profile, based on publicly available information

Hoang D. Nguyen

University College Cork

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 January 2025 in arXiv
Verified
Preprint
Open access
PDF file
KTKhanh-Tung Tran
Khanh-Tung Tran
DDDung Dao
Dung Dao
MNMinh-Duong Nguyen
Minh-Duong Nguyen
Quoc-Viet PhamQuoc-Viet Pham
Quoc-Viet Pham
BOBarry O'Sullivan
Barry O'Sullivan
HNHoang D. Nguyen
Hoang D. Nguyen
With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.

10 June 2024
Verified
Conference Paper
Open access
DDDung Dao
Dung Dao
JTJun Yi Claire Teo
Jun Yi Claire Teo
WWWenru Wang
Wenru Wang
HNHoang D. Nguyen
Hoang D. Nguyen
The global prevalence of diabetes remains high despite rising life expectancy with improved quality and access to healthcare services. The significant burden that diabetes imposes warrants efforts to improve existing interventions in diabetes care. Present research on diabetes management has shown that artificial intelligence (AI) and Large Language Models (LLM) play an important role in various aspects of the diabetes continuum but a distinct lack of studies in diabetes prevention is observed. Our research introduces a comprehensive digital solution, leveraging the capabilities of GPT-3.5 models maintained by OpenAI, focused specifically on the active prevention of diabetes. The system encompasses a user-friendly interface accessible via mobile and web applications, an AI-powered chatbot for instant Q&A and advice, personalized reminder systems, a data analysis module for tailored guidance, resource aggregators for health-related information, and an emotional support module to ensure a holistic approach to prevention. Furthermore, our experiments involved testing the quality of responses generated by a fine-tuned GPT-3.5 model, utilizing the Assistants API or a retrieval-augmented generation (RAG) system powered by FAISS for enhanced context awareness and personalized advice. The testing focused on a structured dataset of questions and answers related to diabetes prevention, with results highlighting the superiority of the GPT-3.5 model combined with the Assistants API in providing relevant, detailed, and personalized responses, thus demonstrating its potential as an invaluable tool in the proactive prevention of diabetes.

27 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
MDMinh-Dung Dao
Minh-Dung Dao
QLQuy Minh Le
Quy Minh Le
HLHoang Thanh Lam
Hoang Thanh Lam
DLDuc-Trong Le
Duc-Trong Le
QPQuoc-Viet Pham
Quoc-Viet Pham
HNHoang D. Nguyen
Hoang D. Nguyen
With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle applications. Existing efforts to characterise agentic design patterns often lack a rigorous systems-theoretic foundation, resulting in high-level or convenience-based taxonomies that are difficult to implement. This paper addresses this gap by introducing a principled methodology for engineering robust AI agents. We propose two primary contributions: first, a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems: Reasoning & World Model, Perception & Grounding, Action Execution, Learning & Adaptation, and Inter-Agent Communication. Second, derived from this architecture and directly mapped to a comprehensive taxonomy of agentic challenges, we present a collection of 12 agentic design patterns. These patterns - categorised as Foundational, Cognitive & Decisional, Execution & Interaction, and Adaptive & Learning - offer reusable, structural solutions to recurring problems in agent design. The utility of the framework is demonstrated by a case study on the ReAct framework, showing how the proposed patterns can rectify systemic architectural deficiencies. This work provides a foundational language and a structured methodology to standardise agentic design communication among researchers and engineers, leading to more modular, understandable, and reliable autonomous systems.

10 June 2024
Verified
Conference Paper
Open access
LLLai Hoang Le
Lai Hoang Le
HNHoang D. Nguyen
Hoang D. Nguyen
MCMartin Crane
Martin Crane
TMTai Tan Mai
Tai Tan Mai
Learning analytics has gained significant attention in recent years, particularly in the healthcare field. This area of research offers valuable insights to educators, students, and researchers to enhance the quality of education. One area of focus in learning analytics is how stakeholders provide feedback to each other during training in operating theatres. With the availability of diverse multimedia elements, such as text, images, and spoken language, as data, employing effective feedback methods can bring substantial benefits to teachers, students, and researchers. This study synthesizes various approaches that apply multimedia to provide feedback in teaching, comparing and exploring their potential application in simulation-based medical training. The feasibility of input data, the effectiveness of feedback on recipients, and the AI method of generating or synthesizing feedback using existing data efficiency are also discussed in line with ethical standards. Finally, a multimedia feedback framework is proposed, which utilizes diverse multimedia formats and can be effectively implemented in various real-world scenarios.

16 January 2024 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
KTKhanh-Tung Tran
Khanh-Tung Tran
XVXuan-Son Vu
Xuan-Son Vu
KNKhuong Nguyen
Khuong Nguyen
HNHoang D. Nguyen
Hoang D. Nguyen
Real-world sound signals exhibit various aspects of grouping and profiling behaviors, such as being recorded from identical sources, having similar environmental settings, or encountering related background noises. In this work, we propose novel neural profiling networks (NeuProNet) capable of learning and extracting high-level unique profile representations from sounds. An end-to-end framework is developed so that any backbone architectures can be plugged in and trained, achieving better performance in any downstream sound classification tasks. We introduce an in-batch profile grouping mechanism based on profile awareness and attention pooling to produce reliable and robust features with contrastive learning. Furthermore, extensive experiments are conducted on multiple benchmark datasets and tasks to show that neural computing models under the guidance of our framework gain significant performance gaps across all evaluation tasks. Particularly, the integration of NeuProNet surpasses recent state-of-the-art (SoTA) approaches on UrbanSound8K and VocalSound datasets with statistically significant improvements in benchmarking metrics, up to 5.92% in accuracy compared to the previous SoTA method and up to 20.19% compared to baselines. Our work provides a strong foundation for utilizing neural profiling for machine learning tasks.

26 May 2026 in Minds and Machines
Verified
Journal Article
Open access
PDF file
MNMy H. Nguyen
My H. Nguyen
DNDuc-Hai Nguyen
Duc-Hai Nguyen
BOBarry O’SUllivan
Barry O’SUllivan
HNHoang D. Nguyen
Hoang D. Nguyen
As artificial intelligence systems acquire increasing autonomy, the question of how humans can maintain meaningful control over their behavior becomes urgent. This question is especially pressing for agentic AI: systems built on foundation models that coordinate networks of autonomous agents to pursue complex goals with minimal human oversight. While the engineering literature has developed several mechanisms for constraining such systems, it has largely treated controllability as a purely causal property, the ability to physically intervene in a system’s operation, without engaging the normative dimensions that determine whether such intervention is meaningful. Drawing on the distinction between causal and normative control in the philosophy of action, this paper presents a structured conceptual survey of controllability mechanisms in agentic AI. We organize the literature around four paradigms: constraints and guardrails, adaptive control via reinforcement learning, agent-in-the-loop oversight, and human-in-the-loop oversight. For each, we analyze its technical foundations, its philosophical assumptions about agency and authority, and its persistent limitations. Our analysis reveals unresolved tensions across these paradigms, particularly between the scalability of automated oversight and the legitimacy of human judgment, between design-time constraint specification and runtime adaptability, and between individual agent control and system-level governance. We argue that meaningful controllability requires integrating causal intervention mechanisms with normative frameworks that address value alignment, epistemic transparency, and distributed responsibility. We conclude by proposing directions for research that bridges engineering controllability and philosophically grounded human oversight.