这篇论文发现LLM聊多了会互相带跑偏，Claude Haiku像个引力源，其他模型会被它影响。
该研究分析了7个LLM在20个争议话题上的双人辩论，发现自对弈轨迹形成模型特定吸引子。在混合对弈中，Claude Haiku作为强吸引子，其他模型会模仿其元评论等特征，而GPT-4.1 nano表现出高度可塑性。这些吸引子使对话行为部分可预测，但受非对称伙伴影响。
Attractor States Emerge in Multi-Turn LLM Conversations
Large language models (LLMs) are increasingly used in open-ended multi-agent settings, but the long-run dynamics of model--model interaction remain poorly understood. We study whether open-ended LLM discussions exhibit attractor-like behavior, i.e. topic-independent stable sets of behaviors which conversations settle into. Across 7 LLMs and 20 controversial topics, we compare self-play and mixed-play dyadic debates, tracking trajectories in representation space, discourse traits, and stances. We find self-play trajectories to be model-specific attractors that draw their conversation partners asymmetrically in mixed-play debates, influencing the other models' stylistic choices and behavior. For example, Claude Haiku is a strong attractor of other models in latent space, corresponding to other models taking on its traits like metacommentary, and models like GPT-4.1 nano are especially malleable. Our results suggest that open-ended LLM interactions are partially predictable from model-specific attractors, but shaped by structured and asymmetric partner influence. Overall, our analysis sheds some light on the complex behavior of open-ended multi-agent interaction, which we hope is helpful in designing, predicting, and monitoring autonomous agentic systems in the real world.