Research & Papers

SupplyNet uses LLM agents to turn supply chain simulation into a visual decision game

Gamified simulation with multi-agent LLMs helps learners explore 'what-if' scenarios actively.

Deep Dive

SupplyNet is a new visual simulation system from researchers Yanjia Li, Kelcy Kexin Han, Tianrui Hu, Yi-Fan Cao, Huamin Qu, and Sicheng Song. It uses a contextual graph-based LLM multi-agent framework to model interdependent supply chain dynamics, turning simulation into a manipulable decision space. The system includes an interactive network view of system state, a branching timeline for 'what-if' exploration and comparison, and a task-oriented analysis console for structured performance breakdowns. These visual components support counterfactual exploration, causal tracing, and comparative reasoning about outcomes.

A user study suggests that SupplyNet increases engagement and supports users' perceived understanding of supply chain dynamics, highlighting the potential of pairing contextual multi-agent simulation with visualization to advance operational comprehension. The paper is 25 pages with 7 figures, submitted to arXiv in June 2026 under Human-Computer Interaction (cs.HC).

Key Points
  • Uses a contextual graph-based LLM multi-agent framework to model interdependent supply chain dynamics.
  • Features three visual components: interactive network view, branching timeline for what-if analysis, and task-oriented console.
  • User study indicates increased engagement and improved perceived understanding of supply chain operations.

Why It Matters

Transforms abstract supply chain data into an explorable, gamified learning tool for professionals and students.

📬 Get the top 10 AI stories daily