I am a second-year PhD student in Data Science & AI at Monash University in Melbourne, Australia. I am supervised by Prof. Dinh Phung, Dr. Thuy-Trang Vu, and Dr. Linhao Luo.
I study safety, autonomy, and robustness in a Society of Intelligent Agents. My research aims to advance agentic systems and frontier models and enable large-scale coordination through agentic collectives and economies. This includes intelligent orchestration and communication, self-improvement, and agentic safety and autonomy. My broader work spans multi-agent coordination, LLM alignment, long-horizon planning and reasoning, retrieval-augmented generation, and model evaluation. My research has been published at EMNLP, COLM, CoNLL, NAACL, and LREC-COLING.
Before starting my PhD, I led LLM and RAG products from experimentation to deployment at MISA and was an AI Research Resident at VinAI Research (now part of Qualcomm), where I worked on weakly supervised learning and information extraction.
Education
Doctor of Philosophy in Data Science & Artificial Intelligence
Monash University · Melbourne, Australia · Jun. 2025–Present
Research: Safe and Autonomous Society of Intelligent Agents.
Supervisors: Prof. Dinh Phung, Dr. Thuy-Trang Vu, and Dr. Linhao Luo.
Bachelor of Computer Science
Hanoi University of Science and Technology · Hanoi, Vietnam · Aug. 2017–Aug. 2021
Thesis: An Uncertainty-Aware Encoder for Aspect Detection.
Best Thesis Presentation Award.
News
- [Paper]: The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems was accepted to AACL-IJCNLP 2026 (Findings).
- [Paper]: TriAlign was accepted to EMNLP 2026.
- [Milestone]: Passed my PhD confirmation milestone with the research proposal Toward Native Social Ability in Society of Intelligent Agents.
- [Paper]: Improving Table Understanding with LLMs and Entity-Oriented Search was accepted to COLM 2025.
- [Paper]: Planning for Success was accepted to CoNLL 2025.
- [Achievement]: Our Vietnamese LLM reached #1 on the VMLU leaderboard.
More News (2024)Hide News (2024)
More News (2023 and before)Hide News (2023 and before)
- [Paper]: A Self-Enhancement Multitask Framework for Unsupervised Aspect Category Detection was accepted to EMNLP 2023.
- [Paper]: An Uncertainty-Aware Encoder for Aspect Detection was accepted to Findings of EMNLP 2021.
- [Award]: Received the Best Thesis Presentation Award at HUST.
Research Notes
Accessible explanations of the ideas behind my research.
How do we scale AI agents without putting one agent in charge of everything?
Paper: A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems
Most multi-agent systems rely on a central orchestrator—but as the team grows, it can become a bottleneck.
When Intelligent Agents Talk, Can Their Biases Become Stronger?
Paper: The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
A short introduction to how stereotypical bias can emerge, spread, and intensify through interactions in multi-agent systems.
Selected Publications
For a complete list, see my Google Scholar profile.
The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
AACL-IJCNLP 2026 (Findings)
Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
CoNLL 2025
Show more publicationsShow fewer publications
SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning
NAACL 2024 · Long Paper
Experience
- — Second-year PhD Student & Research Assistant, Monash University
- — Senior AI Engineer & LLM Team Lead, MISA
- — AI Research Resident, VinAI Research
- — Research Student, Data Science Laboratory, HUST
Academic Service
Teaching
- — Teaching Assistant, Natural Language Processing, Monash University
- — Teaching Assistant, Natural Language Processing, VinUniversity
- — Teaching Assistant, Web Mining and Graph Analytics, HUST