arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.22320cs.MA
收藏

IFS:多智能体临时系统的信息流结构

IFS: Information Flow Structure for Multi-agent Ad Hoc System

College of Electronics;Information Engineering Tongji University Shanghai, China

Yanqing Fu, Chenrun Wang, Chao Huang, Zhuping Wang

AI总结:

针对多智能体临时系统信息流不足与处理能力有限的问题,提出IFS信息流结构,通过通信与信息融合提升性能,在星际争霸II中优于基线并具强泛化能力。

摘要:

多智能体临时系统是动态协作系统,其中多个自主智能体必须在开放环境中与已知和未知的队友合作,且不依赖预先协调的策略。这些系统在不确定性和部分可观测性条件下运行,团队组成、智能体行为和环境因素可能在执行过程中发生变化。通过对此类系统中信息流的分析,我们识别出现有研究的两个关键局限性:信息流不足和信息处理能力有限。为解决这些问题,我们提出了一种用于多智能体临时系统的信息流结构(IFS),该结构从通信和信息融合的角度应对这些挑战。在星际争霸II中的实验结果表明,IFS显著提升了信息流和处理能力,同时在复杂的临时团队协作场景中展现出强大的泛化能力,并优于基线方法。

英文摘要:

Multi-agent ad hoc systems are dynamic collaborative systems in which multiple autonomous agents must cooperate with both known and unknown teammates in open environments, without relying on pre-coordinated strategies. These systems operate under conditions of uncertainty and partial observability, where team composition, agent behaviors, and environmental factors may change during execution. Through an analysis of information flow in such systems, we identify two key limitations in existing research: insufficient information flow and limited information processing capacity. To address these issues, we propose an information flow structure for multi-agent ad hoc systems (IFS), which tackles these challenges from the perspectives of communication and information fusion. Experimental results in StarCraft II demonstrate that IFS significantly improves both information flow and processing capacity, while exhibiting strong generalization capabilities and outperforming baseline methods in complex ad hoc teamwork scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑