为多智能体系统设计向量化信誉传播机制，支持主题感知与高效查询。
TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
- 用主题门控传递算子在交互图上传播多维信誉向量
- 在稠密/稀疏图上分别达到98%和78%的多标签精度@5
- 可抵御洗票、共谋等攻击，适合高安全需求的智能体生态
我们提出TrustFlow，一种信誉传播算法，为每个软件智能体分配一个多维信誉向量而非标量分数。信誉通过交互图传播，利用基于内容嵌入的主题门控转移算子调节每条边，其收敛性由压缩映射定理保证。我们设计了一类Lipschitz-1转移算子与可组合的信息论门控机制，在密集图上实现最高98%的多标签Precision@5，在稀疏图上达78%。在涵盖8个领域的50个智能体基准测试中，TrustFlow对Sybil攻击、信誉清洗和投票圈最多仅造成4个百分点的精度影响。不同于PageRank和主题敏感PageRank，TrustFlow生成的向量信誉可直接通过点积在用户查询同嵌入空间中检索。
原文摘要 · Abstract (English)
We introduce TrustFlow, a reputation propagation algorithm that assigns each software agent a multi-dimensional reputation vector rather than a scalar score. Reputation is propagated through an interaction graph via topic-gated transfer operators that modulate each edge by its content embedding, with convergence to a unique fixed point guaranteed by the contraction mapping theorem. We develop a family of Lipschitz-1 transfer operators and composable information-theoretic gates that achieve up to 98% multi-label Precision@5 on dense graphs and 78% on sparse ones. On a benchmark of 50 agents across 8 domains, TrustFlow resists sybil attacks, reputation laundering, and vote rings with at most 4 percentage-point precision impact. Unlike PageRank and Topic-Sensitive PageRank, TrustFlow produces vector reputation that is directly queryable by dot product in the same embedding space as user queries.
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。