Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation

Joshua C. Yang, Maurice Flechtner, Damian Dailisan, Michiel A. Bakker

Keywords: Large language models, multi-agent systems, cooperative AI, deliberation, civic discourse, belief updating, agent simulation, trustworthy AI

TL;DR: Belief Engine makes LLM agents’ stance changes configurable and inspectable, so deliberative simulations can trace when agents listen, stay committed, converge, or disagree.

Abstract: LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement may reflect evidence uptake, anchoring, role drift, echoing, or changed prompt and retrieval context. We introduce the Belief Engine (BE), an auditable belief-update layer that treats ``belief'' as an evidential state over a proposition and exposes it as scalar stance. BE extracts arguments into structured memory and updates stance with a log-odds rule controlled by evidence uptake $u$ and prior anchoring $a$. Across multiple base LLMs, parameter sweeps show that these controls reliably shape stance dynamics while preserving an evidence-level update trail. On DEBATE, a human deliberation dataset with pre/post opinions, BE best reconstructs participants whose final stance follows extracted evidence; stable and evidence-opposed cases instead point to anchoring or factors outside the extracted evidence stream. BE provides configurable infrastructure for studying evidence-grounded deliberation, where openness, commitment, convergence, and disagreement can be tied to explicit update assumptions rather than hidden prompt effects.

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: 399