通过上下文相关性的注意力引导增强多智能体通信
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
AI总结:
针对LLM多智能体系统中长对话历史导致信息稀释的问题,提出无训练的上下文管理方法Agent-Radar,利用时空衰减机制动态引导注意力,在五个基准上取得最高7.64个绝对点的提升。
摘要:
基于LLM的多智能体系统通过协作推理在复杂任务上表现出色。然而,这些系统在交互过程中会迅速积累极长的对话历史。随着对话变长,相关信息被无关上下文稀释,导致性能下降。在这项工作中,我们提出了Agent-Radar,一种无需训练的上下文管理方法,通过新颖的时空衰减机制动态引导每个智能体的注意力到相关上下文。实验表明,Agent-Radar在五个不同基准上优于最先进的方法,最高提升7.64个绝对点。此外,分析显示Agent-Radar在智能体数量和交互轮次增加时仍然有效且鲁棒。最后,消融研究表明Agent-Radar的核心组件对性能至关重要,且在不同设置下具有泛化性。
英文摘要:
LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely long conversation histories during interaction. As conversations lengthen, relevant information is increasingly diluted by irrelevant context, leading to degraded performance. In this work, we present Agent-Radar, a training-free context management method that dynamically steers each agent's attention toward relevant context with a novel temporal and spatial decay mechanism. Our experiments demonstrate that Agent-Radar outperforms state-of-the-art methods across five different benchmarks, yielding gains of up to 7.64 absolute points. Furthermore, our analysis shows that Agent-Radar remains effective and robust as the number of agents and interaction rounds increases. Finally, the ablation study shows that core components in Agent-Radar are crucial to performance and generalizable in different settings.
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。