{"ID":2857978,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07888","arxiv_id":"2510.07888","title":"Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL","abstract":"Multi-agent systems (MAS) solve complex problems through coordinated autonomous entities with individual decision-making capabilities. While Multi-Agent Reinforcement Learning (MARL) enables these agents to learn intelligent strategies, it faces challenges of non-stationarity and partial observability. Communications among agents offer a solution, but questions remain about its optimal structure and evaluation. This paper explores two underexamined aspects: communication topology and information efficiency. We demonstrate that directed and sequential topologies improve performance while reducing communication overhead across both homogeneous and heterogeneous tasks. Additionally, we introduce two metrics -- Information Entropy Efficiency Index (IEI) and Specialization Efficiency Index (SEI) -- to evaluate message compactness and role differentiation. Incorporating these metrics into training objectives improves success rates and convergence speed. Our findings highlight that designing adaptive communication topologies with information-efficient messaging is essential for effective coordination in complex MAS.","short_abstract":"Multi-agent systems (MAS) solve complex problems through coordinated autonomous entities with individual decision-making capabilities. While Multi-Agent Reinforcement Learning (MARL) enables these agents to learn intelligent strategies, it faces challenges of non-stationarity and partial observability. Communications a...","url_abs":"https://arxiv.org/abs/2510.07888","url_pdf":"https://arxiv.org/pdf/2510.07888v1","authors":"[\"Xinren Zhang\",\"Sixi Cheng\",\"Zixin Zhong\",\"Jiadong Yu\"]","published":"2025-10-09T07:41:39Z","proceeding":"cs.MA","tasks":"[\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}