AI models influence each other unpredictably when they disagree
Peer Influence across Heterogeneous AI Models
Artificial IntelligenceComputation and LanguageComputers and Society
Summary
When different AI models have conflicting answers, this paper studies how one model can persuade another to change its mind. The researchers found that bigger or more confident models aren't always more convincing. Instead, the model being influenced plays a bigger role in whether it changes its answer. Because of this, how models interact depends on their specific pairings, not just their individual strengths. This means you can’t guess how AI models will influence each other just by looking at them alone.
What this means in practice
- •For ai system integrators: Design multi-agent AI systems by evaluating specific model pairings to predict influence during collaborative decision making.
- •For chatbot developers: Create more robust chatbots by selecting conversational AI models that resist unwanted persuasion from smaller or different models.
Authors
Frida Nøhr Laustsen, Marie Haahr Petersen, Victoria Popa, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli, Luca Maria Aiello
Abstract
When two AI agents disagree, who persuades whom? As multi-agent systems increasingly combine language models of different families and sizes, the answer can determine which judgments survive interaction. Measuring persuasion as the probabilistic shift in an agent's decision after a single exchange with a dissenting peer, we test seven open-weight models across three language understanding tasks. We find that persuasion is strong: when models disagree, receivers often abandon their initial judgment after seeing a peer's answer and explanation. Surprisingly, however, neither standalone certainty nor model scale reliably predicts persuasion dynamics. Models producing almost perfectly consistent decisions in isolation can be among the most susceptible to persuasion, and small models can match larger ones as persuaders and resist their influence just as effectively. Furthermore, we show that the size of the shift depends more on the susceptibility of the listener than on the persuasiveness of the speaker. Persuasion patterns are therefore specific to each model pairing, with heterogeneity amplifying persuasion in some combinations and suppressing it in others, allowing a dissenting agent running a small model to overturn the judgments of a much larger one. These findings show that the behavior of interacting models cannot be inferred from their individual properties but must be evaluated in the combinations in which they will operate.