Tag
This paper introduces Boundary_Sync, a protocol measuring representational coupling in multi-agent LLM systems. Experiments with GPT-4o show that communication causes significant homogenization in both text and image modalities, but group size moderates the direction, with larger groups leading to homogenization and smaller groups to diversification.
This paper models multi-agent LLM deliberation as a closed-loop dynamical system where each agent has a hidden internal belief (anchor) that continually pulls its opinion, and shows how this anchor can be recovered from deliberation data alone, explaining phenomena like opinions escaping the convex hull of initial beliefs.
Introduces Think-Before-Speak (TBS), an interval-based multi-agent simulation framework that separates agents' private internal evaluation from public utterance generation, enabling analysis of the pathway from internal states to public expression in social simulations.