ICCBR'25Case-Based Reasoning in Generative Agents: Review and Prospect
Haoxi Zhan, Youlin Wu, jian Ding, Bo Xu, Liang Yang, Hongfei Lin
Abstract
With the rapid pervasion of Generative AI across academia, industry, and society, researchers and the public alike have begun to envision the future of generative agents and their potential role in achieving Artificial General Intelligence (AGI). However, while representative generative AI algorithms have demonstrated impressive language capabilities, they still fall short in complex reasoning tasks. Recent findings in cognitive neuroscience suggest significant differences in the cognitive mechanisms underlying language and reasoning abilities within the human brain. Therefore, AI techniques such as Case-Based Reasoning (CBR), Expert Systems, and Knowledge Representation retain their unique advantages. Case-Based Reasoning, due to its emulation of human memory mechanisms, occupies an important and distinct position in cognitive processes. We argue that CBR will play an indispensable role in future intelligent agents. In this paper, we adopt an interdisciplinary perspective to review relevant research and perspectives from psychology, cognitive science, psychiatry, and artificial intelligence. Building upon this review, we envision future generative agents with case-based reasoning at their core. We propose a technical framework for CBR-based generative agents and discuss potential research avenues.
Poster
Cite our work!
@inproceedings{zhan2025case,
title={Case-Based Reasoning in Generative Agents: Review and Prospect},
author={Zhan, Haoxi and Wu, Youlin and Ding, Jian and Xu, Bo and Yang, Liang and Lin, Hongfei},
booktitle={International Conference on Case-Based Reasoning},
pages={172--186},
year={2025},
organization={Springer}
}