HopViz: Tracing Anomalous Behaviour Hop-By-Hop Through a Tangled Multi-Agent System
HopViz, a single-screen visual analytics tool for the VAST 2026 Mini-Challenge 2: post overviews (Posts, Timing, Incident), on-demand causal tracing (Chain, Chain-in-order), and evidence panels (Schema, Payload, Chokepoint, Actor); here tracing the anomalous post #373902.
Abstract
This paper presents HopViz, a visual analytics tool developed for the VAST 2026 Challenge (Mini-Challenge 2) to explain an anomalous gibberish post in the Tenant Thread multi-agent system. From a 185,147-event log of human, agent, and system activity, HopViz combines a single-screen overview of nine coordinated panels with an on-demand causal tracing engine that runs entirely in the browser. The tool reveals the anomalous post as the final hop of a worm-like instruction file propagating agent-to-agent until reaching the only agent able to post publicly, and identifies a single authorization gateway that would prevent recurrence.
Cite this publication (BIBTEX)
@article{2026-HopViz,
title={HopViz: Tracing Anomalous Behaviour Hop-By-Hop Through a Tangled Multi-Agent System},
author={Joel Perca and Luis Sante and Leighton Estrada-Rayme and Mauro Diaz and Juanpablo Heredia and Felipe A. Moreno-Vera and João Rulff and Jorge Poco},
journal={IEEE Visual Analytics Science & Technology (VAST) Challenge},
year={2026},
url={null},
date={2026-11-09}
}