Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood. We show that dynamically updating LLM-generated reward weights during off-policy MARL violates the stationarity assumption of Potential-Based Reward Shaping (PBRS) and contaminates the experience replay buffer, whose stored transitions carry reward labels computed under stale shaping weights. We characterise the result as a regime-dependent failure whose severity depends on how competent the unshaped baseline already is. To control it we propose two stabilisation strategies: a Phase-Based Freeze Schedule that enforces strict stationarity within training phases, and Exponential Moving Average (EMA) smoothing that bounds per-episode weight drift. We evaluate across three cooperative environments and five random seeds with QMIX, complemented by an exploratory VDN extension, yielding a three-regime taxonomy. In the augmentative regime (Simple Spread), where the baseline is functional (74.4 %), EMA significantly improves success to 86.7 % ($+12.3$ pp, $p<0.01$) while naive dynamic updates collapse it to 15.2 %. In the essential regime (Level-Based Foraging), where the baseline is broken (0.1 %), any shaping unlocks the task (95.9 % under EMA). In the supplementary regime (SMAC 3m), where the baseline is near-saturated (98.8 %), stabilised shaping preserves performance (99.9 %) while unstabilised shaping adds variance without gain. These findings establish reward-signal stationarity as a necessary design constraint and indicate that regime placement is a practical predictor of whether dynamic LLM shaping helps or harms.
A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Department of Computer Science & Engineering, University of Minnesota（明尼苏达大学计算机科学与工程系）；Department of Mechanical Engineering & Materials Science, Yale University（耶鲁大学机械工程与材料科学系）；Computer Vision, BYD COMPANY LIMITED（计算机视觉，比亚迪有限公司）；School of Architecture, University of Texas at Austin（德克萨斯大学奥斯汀分校建筑学院）；Faculty of Applied Science & Engineering, University of Toronto（多伦多大学应用科学与工程学院）
Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Cooperative Resilience in Artificial Intelligence Multiagent Systems
Universidad de los Andes（安第斯大学）；Center of Excellence in Analytics and Artificial Intelligence Bancolombia（哥伦比亚银行分析与人工智能卓越中心）；Universidad de Ibagué（伊瓦格大学）
Online Subset Selection using $α$-Core with no Augmented Regret
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Chennai Mathematical Institute（金奈数学研究所）；Indian Institute of Technology (ISM) Dhanbad（印度理工学院（印度矿业学院）丹巴德分校）；Tata Institute of Fundamental Research（塔塔基础研究所）
Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
Institute of Engineering and Computational Mechanics, University of Stuttgart, 70569 Stuttgart, Germany（工程与计算力学研究所，斯图加特大学，德国斯图加特70569）；Mechanical Engineering, LUT University, 53850 Lappeenranta, Finland（机械工程，卢蒂大学，芬兰拉佩恩兰塔53850）
C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
The Graduate University for Advanced Studies (SOKENDAI)（高级研究大学（SOKENDAI））；National Institute of Informatics（国家信息研究所）；The Asahi Shimbun Company（朝日新闻公司）；The University of Tokyo（东京大学）
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
Australian Artificial Intelligence Institute (AAII), Faculty of Engineering and Information Technology, University of Technology Sydney（澳大利亚人工智能研究所（AAII），悉尼科技大学工程与信息技术学院）
Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Faculty of Data Science, City University of Macau（数据科学学院，澳门城市大学）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)（计算能力网络与信息安全重点实验室，教育部，山东计算机科学中心，齐鲁工业大学（山东科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算能力互联网与服务计算重点实验室，山东省计算机科学基础研究中心）
