arXiv：cs.AI· Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin·· 23 小时前
LLM 多智能体协调的自由度：集中式与去中心化之间
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
AI 导读
研究提出 Degrees of Freedom（DoF）连续配置框架，用于量化 LLM 多智能体系统中委派给下游智能体的决策空间大小，其两端分别对应集中式与去中心化协调。在六个评估状态中的五个，中间 DoF 配置的平均准确率高于两个端点。性能图景依赖任务领域，域内保留经验可让两种分支配置更接近。
正文
Abstract:Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.17751 [cs.MA] |
| (or arXiv:2610.17751v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17751 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yiqing Peng [view email]
[v1]
Tue, 13 Oct 2026 05:32:27 UTC (1,376 KB)
来源：arXiv：cs.AI · arxiv.org