Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

Jul 15, 2026

A preprint investigates how the structure of interaction graphs influences consensus and fragmentation in populations of open-weight language models using a naming-game protocol. The study finds that homophilous (similarity-based) routing amplifies fragmentation, while bridge-seeking routing with memory can restore consensus. Experiments across various model sizes and settings show that retaining interaction history generally shifts dynamics toward consensus, especially in well-mixed populations.

Why it matters: The findings highlight that the design of interaction graphs and memory mechanisms in multi-agent language model systems is crucial for achieving consensus, informing future approaches to decentralized AI coordination.

Full story at: arXiv AI/ML ↗