Trustworthy and Explainable LLM Agents for Interactive Systems
A broader research agenda around making LLM agents more interpretable, controllable, and useful in interactive entertainment and HCI contexts.
Explainability/Trust/Interactive Systems/Human-AI Interaction
This research direction asks how future interactive systems can use LLM agents in ways that remain understandable to designers, researchers, and players.
The work connects technical agent design with HCI questions: how behavior is surfaced, how limitations are communicated, and how people can evaluate whether an agent is behaving responsibly.