MSc(DDM) Expert Sharing Seminar Series - Beyond Personas: AI Roleplay, Generative Agents, and Human Simulation

We are excited to have Mr. Hinz SHUM, Senior Manager (Global AI Model Validation and Governance) at Manulife, to share the topic “Beyond Personas: AI Roleplay, Generative Agents, and Human Simulation”.

All HKUST students are welcome to attend.

Details are as follows.

Date: 6 October 2026 (Tuesday)
Time: 11:00 AM - 12:00 PM HKT
Speaker: Mr, Hinz SHUM, Senior Manager, Global AI Model Validation and Governance, Manulife
Moderator: Prof. Sai-ping LI, Adjunct Professor, Department of Physics, HKUST
Via Zoom: Please contact the MSc DDM Program Office at mscddm@ust.hk for Zoom details.

Seminar Topic and Overview:

Beyond Personas: AI Roleplay, Generative Agents, and Human Simulation

Building on Mr. Hinz SHUM’s previous HKUST seminars on Prompt Engineering and Persona Prompting & LLM-as-a-Judge, this third seminar takes the discussion one step further: from instructing AI and assigning personas to creating AI agents that can maintain roles, remember interactions, pursue goals, and simulate human behaviour.

The seminar explores AI roleplay from a technical and research-oriented perspective, examining how Large Language Models (LLMs) can evolve from stateless persona prompting into stateful generative agents. Key concepts include role conditioning, agent goals and states, memory and retrieval architectures, multi-agent interaction, and the emergence of complex behaviours when multiple role-playing agents interact within a simulated environment.

The seminar will then examine an increasingly important research question: Can LLM-based agents meaningfully simulate humans and human populations? Through examples of generative agents and multi-agent simulations, we will critically explore persona and behavioural fidelity, role drift, correlated agent behaviour, stereotyping, and simulation validity—ultimately asking whether human-like AI behaviour can provide scientifically meaningful insights into real human behaviour.

About the speaker: 

Mr. Hinz SHUM is a Senior Manager in Global AI Model Validation and Governance at Manulife, where he oversees the governance and responsible use of all AI/ML models across Asia. His work focuses on approving all Asia AI models before deploying to production environment with appropriate risk controls, due diligence, and alignment with business and regulatory expectations. He is also an active algorithmic trading practitioner and has served as a mentor to students at various local universities.

Prior to joining Manulife, Mr. Shum held a Manager role at the Hong Kong Monetary Authority, including in the Banking Supervisory Technology Division, where he supported supervisory initiatives relating to the banking sector’s use of AI and emerging technologies. He also served as a Data Scientist in the Research Department, focusing on the application of advanced analytics and new AI developments to operational use cases.

Earlier in his career, he worked as a Statistician specialising in Data Science within the Hong Kong Government, where he contributed to analytics-driven public sector initiatives, drawing on the knowledge and training gained from the HKUST MSc in Data-Driven Modeling Program. 

*Remarks:

1. This is an online seminar.

2. The seminar is open to HKUST students. 

3. Please note that by accessing the virtual meeting, participants consent to the recording of audio, screen content, and video, which may be used by the HKUST MSc in Data-Driven Modeling for news coverage, promotional and advertising purposes, and inclusion on websites, social media platforms, or other communication channels.