[2Yin-A] Poster 3

[2Yin-A-10] Simulating Opinion Dynamics with Grounded LLM Agents in Economic Environments

〇Ryuji Hashimoto^1,2, Masahiro Kaneko^1,3, Ryosuke Takata^1,2, Takehiro Takayanagi^1,2, Kiyoshi Izumi^1,2 (1. Simulacra Inc., 2. The University of Tokyo, 3. MBZUAI)

Keywords:

Opinion dynamics,Multi-agent simulation,Large language model

Opinion dynamics (OD) studies how individual opinions evolve and generate collective patterns such as consensus and polarization. While recent work explores OD using populations of LLM-based agents focusing on opinion exchange, it typically does not incorporate individuals’ lived experiences, such as economic outcomes of past decisions, which play a critical role in shaping opinions. We propose a novel OD simulation framework that grounds LLM-based agents in an economic environment, allowing them to act and receive environmental feedback. Our simulations exhibit coherent OD at both individual and population levels: individual opinions follow structured trajectories shaped by economic experiences, with adverse conditions inducing opinion rigidity, while at the population level, collective opinions co-move with economic conditions, with inequality amplifying polarization and price instability driving larger distributional shifts. These results highlight the importance of grounding LLM-based agents in environments to capture collective OD.