KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement
Published in IEEE Computer Software and Applications Conference (COMPSAC), 2026
Recommended citation: Bravo-Rocca, G., et al. (2026). "KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement." IEEE COMPSAC 2026. https://arxiv.org/abs/2608.02351
KC-Agent is a dual-process cognitive architecture for efficient ML model improvement, developed in the research line on cognitive architectures for agents at the Barcelona Supercomputing Center & Lenovo. It builds on the CAMA framework to enable agents that continuously adapt and improve in real-world environments.
Recommended citation: Bravo-Rocca, G., et al. (2026). “KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement.” IEEE COMPSAC 2026.