Treadstone: A Communication Channel for Human-AI Collaborative Data Analysis
Hyunwook Lee (Soongsil University), Sungbeom Cho (POSTECH), William Benjamin (Independent Researcher), Changhee Lee (Pohang University of Science and Technology), Hyotaek Jeon (POSTECH), Daeun Jeong (Pohang University of Science and Technology), Sungbok Shin (Sogang University), Sungahn Ko (POSTECH), Niklas Elmqvist (Aarhus University)
Jump to Discussion
Presentation
- Session
- Talk to my agent
- Time
- Tuesday, Nov 10, 11:00 – 11:12 (US/Eastern) · session 10:00 – 11:30
- Room
- Hall Essex center
- Presenting from
- Boston
Links
Sign in to access the Paper PDF.
- Supplemental Material(opens in new tab)
Abstract
Coordinating human analysts with autonomous AI agents faces the same challenges as human-to-human collaboration: sharing intermediate results, avoiding conflicts, and maintaining group awareness. Current tools rely on unstructured messaging or single-threaded chatbot interaction, which lack the structure to track evolving hypotheses or link claims to evidence. We propose agentic social data analysis, a collaboration paradigm extending social data analysis with a shared coordination feed modeled on the content timeline in social media services. We instantiate this concept in TREADSTONE, a platform where human and AI agents asynchronously post, link, and contest analytical claims via threaded messages within a shared feed. By allowing agents to proactively broadcast hypotheses and enabling users to steer the analysis through lightweight curation, Treadstone seeks to balance machine autonomy with human analytical control. A qualitative user study shows that Treadstone fosters collaboration while preserving human analytical agency, in contrast to the solitary experience of conventional chatbot interaction.
For Practitioners
Various types of practitioners may find this paper valuable, particularly those looking to communicate with AI agents to analyze complex datasets. Additionally, researchers interested in AI agents and mixed-initiative systems will gain insights into novel paradigms for Human-AI interaction and collaboration. As readers explore our work, they will understand the overarching workflow of agentic visualization systems and see a potential vision for the future of human-agent collaboration---specifically, the multi-agent collaboration for visualization. Furthermore, practitioners can directly interact with the Treadstone platform, experiment with their own data, and weave cohesive analytical conclusions and data stories through human-agent collaboration.