通过动态注意力引导，解决多智能体对话中上下文过载问题。
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
- 引入时空衰减机制，实时筛选对话中相关上下文。
- 在5个基准上提升最多7.64分，且随智能体和轮次增加仍稳定。
- 无需训练，适配复杂协作任务，尤其适合长对话场景。
基于大模型的多智能体系统在复杂任务中展现出卓越的协作推理能力，但交互过程中会迅速积累极长的对话历史。随着对话延长，相关信息被无关上下文稀释，导致性能下降。本文提出Agent-Radar，一种无需训练的上下文管理方法，通过新颖的时间与空间衰减机制，动态引导每个智能体关注相关上下文。实验表明，Agent-Radar在五个不同基准上均优于现有最优方法，性能提升最高达7.64个百分点。分析显示，其在智能体数量和交互轮次增加时依然有效且稳健。消融实验证明，核心组件对性能至关重要，且在多种设置下具有可泛化性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。