TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
This addresses reputation management for software agents in multi-agent ecosystems, offering a novel approach with specific performance gains.
The paper tackles the problem of assigning reputation to software agents in multi-agent ecosystems by introducing TrustFlow, a reputation propagation algorithm that uses multi-dimensional vectors and topic-gated transfer operators, achieving up to 98% multi-label Precision@5 on dense graphs and resisting attacks with at most a 4 percentage-point precision impact.
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.