[2506.18651] Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination

Computer Science > Artificial Intelligence arXiv:2506.18651 (cs) [Submitted on 23 Jun 2025 (v1), last revised 2 Mar 2026 (this version, v2)] Title:Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination Authors:Shuocun Yang, Huawen Hu, Xuan Liu, Yincheng Yao, Enze Shi, Shu Zhang View a PDF of the paper titled Structured Diversity Control: A Dual-Level Framework for Group-Aware Multi-Agent Coordination, by Shuocun Yang and Huawen Hu and Xuan Liu and Yincheng Yao and Enze Shi and Shu Zhang View PDF HTML (experimental) Abstract:Controlling the behavioral diversity is a pivotal challenge in multi-agent reinforcement learning (MARL), particularly in complex collaborative scenarios. While existing methods attempt to regulate behavioral diversity by directly differentiating across all agents, they lack deep characterization and learning of multi-agent composition structures. This limitation leads to suboptimal performance or coordination failures when facing more complex or challenging tasks. To bridge this gap, we introduce Structured Diversity Control (SDC), a framework that redefines the system-wide diversity metric as a weighted combination of intra-group diversity, which is minimized for cohesion and inter-group diversity, which is maximized for specialization. The trade-off is governed by a pre-set Diversity Structure Factor (DSF), allowing for fine-grained, group-aware control over the collective strategy. Our method directly constrain...