提出去中心化协议SAC，让多个大模型协作时抵抗恶意干扰。
Robust Multi-Agent LLMs under Byzantine Faults
- 各智能体互评回复，过滤不可靠信息并迭代优化输出。
- 在数学与常识推理任务中，对抗攻击下性能仍显著优于旧方法。
- 适合构建可靠分布式AI系统的研究者与工程师参考。
大型语言模型代理正通过点对点网络协作以提升可靠性，但此类交互也可能引入不可靠或拜占庭式代理，导致错误信息传播并降低整体系统性能。为此，我们提出自锚定共识（SAC）——一种完全去中心化的滤-修协议，代理通过迭代交换回应，本地评估并过滤不可靠消息，同时优化自身输出。我们给出了通信图上的(F+1)-鲁棒性条件，确保诚实代理能在拜占庭影响下仍保持并传播可靠信息。在涵盖开放与闭源权重的多种LLM上，针对数学与常识推理基准的实验表明，SAC能有效抑制拜占庭影响，并在不同通信拓扑下持续提升性能；而先前方法在拜占庭攻击下则明显退化。
原文摘要 · Abstract (English)
Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also introduce vulnerability to unreliable or Byzantine agents that can propagate incorrect information and degrade overall system performance. To address this, we propose Self-Anchored Consensus (SAC), a fully decentralized filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present $(F{+}1)$-robustness conditions on the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments across diverse open- and closed-weight LLMs on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade significantly under Byzantine attacks.
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。