In heterogeneous system of AI agents, when agents disagree, who persuades whom? We found: 1) Models easily influence each other 2) Model size/certainty doesn't imply resistance to influence 3) Opinion shift is determined mostly by the resistance of the hearer. Preprint: arxiv.…
AI Weekly's analysis
→
- Across seven open-weight models and three tasks, a dissenting small model can overturn the judgment of a much larger one.
- Neither standalone certainty nor model scale reliably predicts how a model behaves inside a multi-agent exchange.
- The size of a persuasion shift depends more on the listener's susceptibility than on the speaker's persuasiveness.
Read full analysis →
