VAST Challenge

Organelles: Visual Analytics for Governing Federated Multi-Agent Organizations

Andralyn Yao (Stanford University), Sizheng Cailean Chen (West Lafayette Junior Senior High School), Aaron Wang (University of British Columbia), Justin Li (Carmel High School), Jasmine Tang (McGill University), Nabin Khanal (Purdue University), Qi Yang (Purdue University), Hannah Yanhua Zong (Purdue University ), Jieqiong Zhao (Augusta University), Yingjie Victor Chen (Purdue University), Zhenyu Cheryl Qian (Purdue University)


Jump to Discussion

Links

Top of the first page of the paper “Organelles: Visual Analytics for Governing Federated Multi-Agent Organizations”.

Abstract

How can organizations coordinate and govern multiple autonomous AI agents while maintaining alignment, accountability, adaptability, and effective human oversight? We propose Organelles, a visual analytics system that integrates multiple coordinated views to depict agents’ organizational structure, permissions, communication flows, actions, and alignment status. A compact Petal glyph encodes each agent’s security clearance, permission scope, and activity volume, making actions that exceed expected authority visually salient. By consistently representing alignment status and violations across structural, temporal, and overview views, Organelles helps analysts identify emerging alignment risks, detect potentially unauthorized actions, and monitor the flow of sensitive information. Demo video available at: https://youtu.be/-RDnvPUvXlc. Index Terms: Multi-agent systems, Agentic AI, Authorization, Glyph Design, Visual Analytics.