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.

翻译：我们提出TrustFlow，一种信誉传播算法，该算法为每个软件智能体分配一个多维信誉向量而非标量得分。信誉通过交互图进行传播，借助主题门控传递算子根据每条边的内容嵌入对边进行调制，并由压缩映射定理保证收敛至唯一不动点。我们开发了一系列Lipschitz-1传递算子及可组合的信息论门控机制，在密集图中实现了高达98%的多标签Precision@5，在稀疏图中达到78%。在涵盖8个领域的50个智能体基准测试中，TrustFlow抵抗女巫攻击、信誉洗白及投票圈套时，精度影响最多不超过4个百分点。与PageRank和主题敏感PageRank不同，TrustFlow生成的向量信誉可直接通过点积在与用户查询相同的嵌入空间中进行查询。