Belief Engine: Configurable Opinion Dynamics for Reliable LLM Agent Simulation

Joshua C. Yang, Damian Dailisan, Maurice Flechtner

Keywords: Large Language Models, Opinion Dynamics, Social Simulation, Belief Updating, AI Safety, Participatory Design

TL;DR: We introduce the Belief Engine, a configurable architecture that externalises opinion dynamics to enable stable, reproducible, and transparent social simulations with LLM agents.

Abstract: Large Language Model (LLM) agents can debate fluently, but they do not reliably maintain beliefs across long interactions. This makes it difficult to use them for opinion-dynamics studies where trajectories must be stable, interpretable, and reproducible. We introduce the Belief Engine, a configurable belief architecture that externalises belief state and updates it from extracted arguments. The engine stores adjudicated evidence in memory and updates a bounded stance score using a simple Bayesian log-odds rule with tunable parameters controlling evidence sensitivity, anchoring, and asymmetric weighting. In controlled two-agent debates across topics, we show that Belief Engine produces stance trajectories that are smoother and more reproducible than LLM-based updating, and that its parameters provide monotonic control over persuadability and resistance. By separating what an agent says from how its beliefs are updated, the framework enables traceable and controllable opinion dynamics in LLM-agent simulations.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 7