共识被「更大模型」吸走：UTokyo Matsuo 组 Influencer，七家族命名博弈

View PDF HTML (experimental)

Abstract:Multi-agent LLM systems are increasingly used in practice, but their behavior is complex and hard to understand. We design a simple task to ask which model has the most influence on the final consensus when several models are mixed in one system. Experimentally, across seven model families, we find that the opinions of the other models are absorbed into the opinion of the stronger model, the one with more parameters. This happens even though the task requires no pretraining knowledge and has no correct answer. To understand this phenomenon, we interpret the agents as weighted particles moving on a simplex. Larger models carry a larger weight and therefore occupy a deeper well in the energy landscape. A large weight means strong in-context learning: a model with a large weight amplifies the majority of its context. Larger models are generally better at in-context learning, and this is what makes the larger model the influencer. We hope that this work helps to interpret multi-agent systems, whose behavior is becoming too complex for humans to understand.

Submission history

From: Gouki Minegishi [view email]
[v1] Thu, 22 Oct 2026 11:15:49 UTC (1,777 KB)