# TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems

arXiv: https://arxiv.org/abs/2603.19452 · HTML: https://mlsanity.com/paper/2603.19452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 2 of 2)

- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents](https://mlsanity.com/paper/2509.04979/) (2025)

## Abstract (arXiv)

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.