5 papers
MIVAIS: A Study Environment for Multi-Agent Mixed-Initiative Visual Analytics Applications
Tobias Stähle, Simon Schneider, Rita Sevastjanova +1
Mixed-initiative Visual Analytics (VA) systems empower human users by interleaving human intuition with software agents and their machine intelligence. However, the development and…
GuidedRAG: Semantic Steering of Retrieval-Augmented Generation
Matthijs Jansen op de Haar, Tobias Stähle, Lorenzo Gatti
In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage and semantic steering during r…
From Interaction to Intent: Inferring User Objectives from Provenance Logs
Steffen Holter, Tobias Stähle, Arpit Narechania +1
The ability to automatically infer analytic intent from user interaction histories could enable interactive AI systems to proactively assist users during exploratory data analysis.…
All Relations Lead to Rome: Automated Knowledge Graph Creation and Question Generation
Matthijs Jansen op de Haar, Tobias Stähle, Lorenzo Gatti
Large language models have substantially improved information retrieval and question answering; however, existing datasets generally support either vector-based retrieval over unst…
VACP: Visual Analytics Context Protocol
Tobias Stähle, Péter Ferenc Gyarmati, Thilo Spinner +3
The rise of AI agents introduces a fundamental shift in Visual Analytics (VA), in which agents act as a new user group. Current agentic approaches - based on computer vision and ra…