AINeutralarXiv – CS AI · 6h ago6/10
🧠
Hidden Anchors in Multi-Agent LLM Deliberation
Researchers model multi-agent LLM deliberation as a dynamical system where each agent maintains a hidden internal belief (anchor) that influences its opinions across discussion rounds. The study reveals that agents can escape the convex hull of initial beliefs through deliberation, a behavior unexplained by classical consensus models, and demonstrates that these anchors can be recovered and validated across open-weight model families.