为联邦多智能体系统设计隐私保护新范式，兼顾安全与性能。
Privacy-Enhancing Paradigms within Federated Multi-Agent Systems
- 引入嵌入式隐私代理，集成于检索增强生成阶段
- 在保持系统性能前提下显著提升隐私保护能力
- 适合关注联邦学习中隐私安全的开发者与研究者
基于大语言模型的多智能体系统在解决复杂问题上表现出色，但敏感领域面临新的隐私保护挑战。本文提出联邦多智能体系统（Federated MAS），揭示其与传统联邦学习的根本差异。针对智能体间异构隐私协议、多方对话结构差异及动态对话网络结构等关键挑战，提出嵌入式隐私增强代理（EPEAgent），无缝集成于检索增强生成（RAG）阶段与上下文检索环节，最大限度减少数据流转，仅共享任务相关且智能体特定的信息。同时构建了综合性评估数据集。大量实验表明，EPEAgent在维持系统高性能的同时有效增强了隐私保护。代码将公开于 https://github.com/ZitongShi/EPEAgent。
原文摘要 · Abstract (English)
LLM-based Multi-Agent Systems (MAS) have proven highly effective in solving complex problems by integrating multiple agents, each performing different roles. However, in sensitive domains, they face emerging privacy protection challenges. In this paper, we introduce the concept of Federated MAS, highlighting the fundamental differences between Federated MAS and traditional FL. We then identify key challenges in developing Federated MAS, including: 1) heterogeneous privacy protocols among agents, 2) structural differences in multi-party conversations, and 3) dynamic conversational network structures. To address these challenges, we propose Embedded Privacy-Enhancing Agents (EPEAgent), an innovative solution that integrates seamlessly into the Retrieval-Augmented Generation (RAG) phase and the context retrieval stage. This solution minimizes data flows, ensuring that only task-relevant, agent-specific information is shared. Additionally, we design and generate a comprehensive dataset to evaluate the proposed paradigm. Extensive experiments demonstrate that EPEAgent effectively enhances privacy protection while maintaining strong system performance. The code will be availiable at https://github.com/ZitongShi/EPEAgent
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。