Treadstone: A Social-Media-Inspired Platform for Multi-Agent Collaborative Data Analysis

2026-09-17

AI Summary

研究提出Treadstone平台，通过模仿社交媒体的内容时间线，解决人与AI协作分析数据时的共享、冲突和意识问题。

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.

Problem

• Multi-Agent Collaborative Data Analysis
• Human-AI Collaboration
• Social Media Inspired Platform

Innovation

• agentic social data analysis
• shared coordination feed
• threaded messages
• asynchronous collaboration
• human-analytical agency