Modelling autonomous emotional AI-driven agents in their spatiotemporal context
The research investigates how large language models (LLMs) emerge as reservoirs of a vast array of human experiences, behaviours, and emotions. Building upon prior work of the JRC on synthetic populations , it presents a complete step-by-step guide on how to use LLMs to create highly realistic modelling scenarios and complex societies of autonomous emotional AI agents. This technique is aligned with agent-based modelling (ABM) and facilitates quantitative evaluation.
The report describes how the agents were instantiated using LLMs, enriched with personality traits using the ABC-EBDI model, equipped with short- and long-term memory, and access to detailed knowledge of their environment. This setting of embodied reasoning significantly improved the agents' problem-solving capabilities and when subjected to various scenarios, the LLM-driven agents exhibited behaviours mirroring human-like reasoning and emotions, inter-agent patterns and realistic conversations, including elements that mirrored critical thinking.
These LLM-driven agents can serve as believable proxies for human behaviour in simulated environments presenting vast implications for future research and policy applications, including studying impacts of different policy scenarios. This bears the opportunity to combine the narrative-based world of foresight scenarios with the advantages of quantitative modelling
HRADEC Jiri;
OSTLAENDER Nicole;
BERNINI Alba;
Hradec, J., Ostlaender, N. and Bernini, A., FABLES: Framework for Autonomous Behaviour-rich Language-driven Emotion-enabled Synthetic populations., Publications Office of the European Union, Luxembourg, 2023, doi:10.2760/858605, JRC135070.
2023-10-13
Publications Office of the European Union
JRC135070
978-92-68-08087-0 (online),
978-92-68-08086-3 (print),
1831-9424 (online),
1018-5593 (print),
EUR 31683 EN,
OP KJ-NA-31-683-EN-N (online),
OP KJ-NA-31-683-EN-C (print),
https://publications.jrc.ec.europa.eu/repository/handle/JRC135070,
10.2760/86682 (online),
10.2760/858605 (print),
