[2H4-GS-11] AI and Society:

[2H4-GS-11-05] An Examination of the Propagation Characteristics of Bad News among LLM Agents and a Proposal for a Human-Mimetic Agent

〇Sogo Kuroda¹, Takayuki Ito¹ (1. Kyoto University)

Keywords:AI reliability, simulation, multi agent

The phenomenon of the rapid spread of bad news is widely recognized in human society, but it is unclear whether the same phenomenon occurs in a community of LLM agents. In this study, we examined whether bad news spreads more easily among LLM agents, and confirmed that bad news tends to propagate less easily than good news. We also proposed a human-mimetic agent to resolve the difference in information propagation characteristics between humans and LLM agents, and showed results that contribute to improving the accuracy of simulation studies.