This study investigates the feasibility and effectiveness of using Large Language Models (LLMs) to drive the evolution of agent-based rules in computational modeling systems.
@inproceedings{jwalapuram2025lear,title={LEAR: LLM-Driven Evolution of Agent-Based Rules},author={Gurkan, Can and Jwalapuram, Narasimha Karthik and Wang, Kevin and Danda, Rudy and Rasmussen, Leif and Chen, John and Wilensky, Uri},year={2025},month=jul,day={14},booktitle={Proceedings of the Genetic and Evolutionary Computation Conference Companion},series={GECCO '25 Companion},publisher={Association for Computing Machinery},address={New York, NY, USA},doi={10.1145/3712255.3734368},url={https://doi.org/10.1145/3712255.3734368},}
QD-LEAR: Exploring Quality-Diversity Tradeoffs in LLM-Evolved Agent Rule Representations
Narasimha Karthik Jwalapuram, Can Gurkan, Kevin Wang, and 4 more authors
In Proceedings of the 2025 Conference on Artificial Life, Jul 2025
Research exploring quality-diversity tradeoffs in Large Language Model-evolved agent rule representations for computational modeling systems.
@inproceedings{jwalapuram2025qdlear,title={QD-LEAR: Exploring Quality-Diversity Tradeoffs in LLM-Evolved Agent Rule Representations},author={Jwalapuram, Narasimha Karthik and Gurkan, Can and Wang, Kevin and Danda, Rudy and Rasmussen, Leif and Chen, John and Wilensky, Uri},year={2025},month=jul,booktitle={Proceedings of the 2025 Conference on Artificial Life},series={ALife 2025},publisher={MIT Press},address={Kyoto, Japan},}