AI 中文总结
研究开放权重语言模型群体中惯例形成，通过命名游戏协议，利用受限首令牌分数构建状态相似性图，对比不同路由方式在多模型网格中的表现，发现保留历史有助于趋向共识，相关特征可用于诊断。
AI 中文摘要
多智能体语言模型系统越来越多地进行局部交互路由，但运行时交互图常被视为实现细节。我们用命名游戏协议研究了参数在11亿到320亿之间的开放权重语言模型群体中的惯例形成。通过对分词器安全标签的受限首令牌分数，测量提示条件分数状态分布，构建状态相似性图，并区分采样标签一致性和潜在状态空间共识。在主要的开放权重修复网格中，保留伙伴标签证据必要但不充分：同质性阈值相似性路由会删除跨盆地暴露并加剧碎片化，而寻桥路由在有内存时通常能修复碎片化。在三种子混合四模型网格中，阈值相似性在189次设置种子运行中未产生最终行为或状态共识，而状态组件和标签分歧桥在14/18次保留内存运行中恢复了最终行为共识。在同质模型群体中，保留历史通常会使碎片化动态趋向共识。对状态阈值、群体规模和词汇量的鲁棒性保持了定性排序，早期窗口图能量特征提供了有用的网格内诊断。
英文摘要
Multi-agent language-model (LM) systems often determine which agents communicate, yet routing is usually treated as an implementation detail. We ask whether routing itself determines whether a population converges on a shared convention or fragments into persistent cliques. We study open-weight agents spanning 1.1B-32B parameters in a controlled naming game, tracking both emitted labels and full first-token preference distributions over the allowed labels. Similarity-based routing can isolate emerging conventions and sustain fragmentation even when every agent interacts in every round. Matched controls show that this effect is not explained solely by uneven participation or model-family-specific score preferences: random rematching and policies that connect disagreeing groups improve coordination when partner-label history is retained, but not when it is absent. Exposure alone is nevertheless insufficient, as some mixed-model populations remain divided despite frequent cross-family interaction, although the same models coordinate homogeneously. Trajectory and controlled-history analyses further distinguish reaching consensus from maintaining it. Finally, ARC-Challenge and MMLU experiments show that routing changes how correct and incorrect answers propagate without reliably improving accuracy. These results establish the runtime interaction graph as a causal design variable whose effects depend jointly on memory, model response, and population composition.
CommentsRevised and expanded version with additional matched routing controls, population-composition experiments, consensus-persistence analyses, task-grounded evaluations, and expanded reproducibility details
