Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）；Huawei Technologies Ltd.（华为技术有限公司）；Beijing University of Posts and Telecommunications（北京邮电大学）
Multi-agent architectures built on large language models (LLMs) have demonstrated the potential to realize swarm intelligence through well-crafted collaboration. However, the substantial burden of manual orchestration inherently raises an imperative to automate the design of agentic workflows. We frame such an agent coordination challenge as a classic problem in dynamic ad-hoc networking: How to establish adaptive and reliable communication among a scalable number of agentic hosts? In response to this unresolved dilemma, we introduce RAPS, a reputation-aware publish-subscribe paradigm for adaptive, scalable, and robust coordination of LLM agents. RAPS is grounded in the Distributed Publish-Subscribe Protocol, allowing LLM agents to exchange messages based on their declared intents rather than predefined topologies. Beyond this substrate, RAPS further incorporates two coherent overlays: (i) Reactive Subscription, enabling agents to dynamically refine their intents; and (ii) Bayesian Reputation, empowering each agent with a local watchdog to detect and isolate malicious peers. Extensive experiments over five benchmarks showcase that our design effectively reconciles adaptivity, scalability, and robustness in a unified multi-agent coordination framework.
A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systems
University of Edinburgh（爱丁堡大学）
ad hoc协调问题是指在没有事先协调机制的多智能体系统中设计一个能够实现最佳灵活性和效率的自主智能体。我们概念化这个问题正式使用博弈论模型，称为随机贝叶斯博弈，其中的行为的球员是由其私人信息，或类型。基于这个模型，我们推导出一个解决方案，称为Harsanyi-Bellman Ad Hoc Coordination（HBA），它利用贝叶斯纳什均衡的概念，在规划过程中找到贝尔曼最优控制意义上的最佳行动。我们评估HBA在多智能体物流领域称为基于水平的觅食，它实现了更高的灵活性和效率比几种替代算法。我们还报告了一个公共科学展览中的人机实验，其中人类参与者反复扮演囚徒困境和石头剪刀布对HBA和替代算法，表明HBA实现了相同的效率和显着更高的福利和胜率。
Bar Ilan University（巴伊兰大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；The University of Edinburgh（爱丁堡大学）；The University of Birmingham（伯明翰大学）；Sony AI（索尼人工智能）
SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking
1 School of Elect. Inform. \& Commun., Huazhong Univ. of Science \& Technology, China；2 Peng Cheng Laboratory, Shenzhen, China；3 Pazhou Laboratory (Huangpu), Guangzhou, China；4 Department of Electrical；Computer Engineering, the University of Arizona
Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
C$^{2}$DL, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所C²DL实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；University of Science and Technology of China（中国科学技术大学）；Qwen Team, Alibaba Group（阿里集团Qwen团队）
K-level Reasoning for Zero-Shot Coordination in Hanabi
Facebook AI Research（脸书人工智能研究院）；University of Oxford（牛津大学）
在合作的多代理设置的标准问题设置是自我发挥（SP），其目标是训练一个团队的代理一起工作。然而，最佳SP策略通常包含任意约定（“握手”），并且与其他独立训练的代理或人类不兼容。后一种需求最近由Hu等人（2020）正式定义为zero-shot协调（ZSC）设置，并部分通过他们的模拟游戏（OP）算法解决，该算法在纸牌游戏Hanabi中显示了改进的ZSC和人类AI性能。OP假设可以访问环境的对称性，并防止代理在训练期间以相互不兼容的方式破坏这些对称性。然而，正如作者所指出的，发现给定环境的对称性是一个计算上的难题。相反，我们表明，通过简单的k级推理（KLR）Costa Gomes et al. 2006，同步训练所有级别，我们可以在Hanabi中获得有竞争力的ZSC和ad-hoc团队合作性能，包括与类人代理机器人配对时。我们还介绍了一种新的方法，同步k级推理与最佳响应（SyKLRBR），它进一步提高了我们的同步KLR的性能，通过共同训练的最佳响应。
