Keywords: Generative AI, Agent Simulation, Text
Need: The use of Large Language Models (LLMs) as autonomous agents is an emerging field generating significant interest across multiple domains. In this paradigm, an LLM (or collection of models) is prompted to take on specific roles, interact with its environment, maintain memory, and use tools to achieve defined objectives.
This project will explore how such agents can model healthcare scenarios, enabling simulation of complex, multi-actor interactions and non-linear outcome pathways—areas often challenging for traditional modelling approaches. An area of particular interest is how an LLM might act as an “intelligence layer” from different agent viewpoints within the same simulated environment.
Complex logs of actions and interactions can then be analysed to understand how scenarios play out and iteratively improve simulation realism. The project will deliver an initial working example based on a simplified care pathway, with the ability to expand to more complex simulations and integrate emerging techniques as the field evolves.
Current Knowledge/Examples & Possible Techniques/Approaches:
Related Previous Internship Projects: N/A - this is first year of the project
Enables Future Work: Foundation for both using agents for evaluation and as an intelligence layer in agent based modelling
Outcome/Learning Objectives:
Datasets: Much of the work will focus on setting up appropriate scenarios and generating outputs from them, but open healthcare datasets will be used to augment where required
Desired skill set: When applying please highlight any experience around work with agent-based modelling, natural language processing, large language models, python coding experience and software development (including any coding in the open), and any other data science experience you feel relevant.
Return to list of all available projects.