用时空图模型防范大模型多智能体协作中的幻觉与错误传播
GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling
- 将多智能体协作建模为时序属性图，追踪错误传播路径
- 无监督架构实现异常节点与边的精准识别，准确率领先
- 基于信息瓶颈理论的图抽象压缩技术，兼顾效率与关键模式保留
大型语言模型的兴起使得能够进行复杂多轮对话的智能体成为可能。然而，多智能体协作面临幻觉放大、错误注入与传播等关键安全挑战。本文提出GUARDIAN，一种统一的方法，用于检测和缓解智能体协作中的多种安全问题。通过将多智能体协作过程建模为离散时间的时序属性图，GUARDIAN显式捕捉了幻觉与错误的传播动态。其无监督编码器-解码器架构结合增量训练范式，从潜在嵌入中重建节点属性与图结构，实现了对异常节点与边的前所未有的精确识别。此外，我们引入基于信息瓶颈理论的图抽象机制，压缩时序交互图的同时保留核心模式。大量实验表明，GUARDIAN在防护大模型多智能体协作免受多样化安全漏洞影响方面表现出色，以高效资源利用达成业界最优准确率。代码已公开于https://github.com/JialongZhou666/GUARDIAN。
原文摘要 · Abstract (English)
The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilities, achieving state-of-the-art accuracy with efficient resource utilization. The code is available at https://github.com/JialongZhou666/GUARDIAN
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。