LLM对话会陷入特定行为模式，像引力吸引其他模型。
Attractor States Emerge in Multi-Turn LLM Conversations
- 通过追踪对话轨迹，发现不同LLM有独特吸引行为
- 自对战中形成稳定行为模式，影响对手风格选择
- 适合研究自主智能体系统设计与风险监控
大型语言模型（LLMs）在开放式多智能体场景中的应用日益广泛，但其长期交互动态仍不明确。我们研究了开放式的LLM对话是否表现出类似吸引子的行为——即与话题无关的稳定行为集合，使对话最终趋于收敛。在7个LLM和20个争议性话题上，比较了自对战与混合对战双人辩论，追踪表示空间、话语特征与立场演变轨迹。结果发现，自对战轨迹形成模型特异的吸引子，且在混合对战中对其他模型产生不对称影响，改变其风格与行为。例如，Claude Haiku 在隐空间中是强吸引子，促使其他模型采用其元评论等特征；而 GPT-4.1 nano 模型尤为易受影响。结果表明，开放式LLM交互部分可由模型特异吸引子预测，但受结构化且非对称的伙伴影响塑造。本研究为理解多智能体复杂行为提供了洞见，有助于未来自主代理系统的构建、预测与监控。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。