arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.18005cs.MAcs.AIcs.CL
收藏

多智能体大语言模型系统中的多样性崩溃:结构耦合与开放性创意生成中的集体失败

Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation

National University of Singapore(国立新加坡大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Nuo Chen, Yicheng Tong, Yuzhe Yang, Yufei He, Xueyi Zhang, Qingyun Zou, Qian Wang, Bingsheng He

AI总结:

研究探讨了多智能体系统在开放性创意生成中多样性崩溃的原因,揭示了结构耦合导致的集体失败,强调了在设计创意任务时保持独立性和分歧的重要性。

摘要:

多智能体系统(MAS)日益用于开放性创意生成,基于集体互动能拓宽探索多样性的期望。然而,何时以及为何这种协作真正扩大了解决方案空间仍不清楚。本文系统地研究了基于MAS的创意生成中三个自下而上的层面:模型智能、智能体认知和系统动态的多样性。在模型层面,我们识别出一个计算效率悖论,即更强、高度对齐的模型尽管单样本质量更高,但边际多样性却下降。在认知层面,权威驱动动态相比由初级成员主导的群体会抑制语义多样性。在系统层面,群体规模扩大导致回报递减,密集的通信拓扑加速了提前收敛。我们将这些结果描述为由结构耦合引起的集体失败,即互动无意中收缩了智能体探索并触发多样性崩溃。我们的分析表明,这种崩溃主要源于交互结构而非模型本身的不足,强调在设计创意任务的MAS时保持独立性和分歧的重要性。我们的代码可在https://github.com/Xtra-Computing/MAS_Diversity获取。

英文摘要:

Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the solution space remains unclear. We present a systematic empirical study of diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics. At the model level, we identify a compute efficiency paradox, where stronger, highly aligned models yield diminishing marginal diversity despite higher per-sample quality. At the cognition level, authority-driven dynamics suppress semantic diversity compared to junior-dominated groups. At the system level, group-size scaling yields diminishing returns and dense communication topologies accelerate premature convergence. We characterize these outcomes as collective failures emerging from structural coupling, a process where interaction inadvertently contracts agent exploration and triggers diversity collapse. Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency, highlighting the importance of preserving independence and disagreement when designing MAS for creative tasks. Our code is available at https://github.com/Xtra-Computing/MAS_Diversity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑