SOURCE-LINKED INTELLIGENCE

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one another. We ask whether that appearance rests on a model of the partner's mind or on the surface record of what the partner said. We build a social simulation in which both questions have exact answers: 40 multi-issue negotiations whose hidden preference weights and whose full Pareto frontier are known by construction. Two model families negotiate across 160 dyads, every transcript is frozen before any measurement, and 2880 counterfactual probes the

Read original source ↗ Open in workspace

recordType

paper

region

Global