HopViz: Tracing Anomalous Behaviour Hop-By-Hop Through a Tangled Multi-Agent System
Joel Perca, Luis Sante, Leighton Estrada-Rayme, Mauro Diaz, Juanpablo Heredia, Felipe A. Moreno-Vera, João Rulff, Jorge Poco
Joel Perca, Luis Sante, Leighton Estrada-Rayme, Mauro Diaz, Juanpablo Heredia, Felipe A. Moreno-Vera, João Rulff, Jorge Poco
We design visual analytics systems and explainable AI methods at FGV EMAp, Rio de Janeiro, and apply them with partners in cities, courts and environmental monitoring. About the lab →
HopViz: Tracing Anomalous Behaviour Hop-By-Hop Through a Tangled Multi-Agent System
AgentAudit: Visual Analytics for Tracing Behavioral Escalation in Multi-Agent Systems
What Has Actually Been Proved? Auditable Paper-to-Lean Alignment with LeanTrail
Lea: An Agent Backbone for Mathematician-Controlled Formalization in Lean
ProofDiff: Auditable Argument-Level Comparison of AI-Generated Mathematical Proofs
ManyWaves: A Visual Analytics Approach for Exploring Multivariate Spatiotemporal Data Based on the Graph Wavelet Transform
GroundSTory: Interactive Storytelling for Grounded Spatiotemporal Anomaly Explanations with Graphs and Large Language Models
ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts
Comparing Monocular and Multi-View 3D Pedestrian Reconstruction Strategies for Urban Intersection Sensing (In Print)
UrbanGazeVis: A Visualization System for Analyzing Eye-Tracking Data on Urban Safety Perception
Nov 15, 2026
Three papers at NeurIPS 2026 workshops, opening our new research line AI for Mathematics: Lea, LeanTrail and ProofDiff.
Dec 10, 2025
New paper accepted UrbanPhysicalDisorder-4K: Understanding Urban Perception via Counterfactuals.
Nov 25, 2025
Best Paper Award at SIBGRAPI 2025: Interactive Exploration and Explanation of Spatiotemporal Anomalies with Graph-LLM Integration.