SupplyNet: Supporting visual exploratory learning in supply chain via contextual multi-agent simulation
Visual Informatics · 2026-07 · 100345
DOI: 10.1016/j.visinf.2026.100345 ↗Kurz gefasst
Fachartikel in der Zeitschrift Visual Informatics, 2026-07. Verfasst von Yanjia Li und 5 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Simulation has long supported supply chain management instruction by letting learners observe network behavior and test decision strategies. Recent progress in LLM-driven agents opens new possibilities for richer, more adaptive simulations, but many existing systems still present abstract, opaque data that overwhelms learners and discourages active exploration. We introduce \textit{SupplyNet}, a gamified visual simulation system built on a contextual graph-based LLM multi-agent framework that models interdependent supply chain dynamics and provides responsive feedback through tiered challenges. \textit{SupplyNet} turns the simulation into a manipulable decision space by integrating 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. Together, these visual components support counterfactual exploration, causal tracing, and comparative reasoning about outcomes. A user study suggests that \textit{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.
Zitieren
APA
Li, Y., Han, K. K., Hu, T., Cao, Y., Qu, H., & Song, S. (2026). SupplyNet: Supporting visual exploratory learning in supply chain via contextual multi-agent simulation. Visual Informatics, 100345. https://doi.org/10.1016/j.visinf.2026.100345
Vancouver
Li Y, Han KK, Hu T, Cao Y, Qu H, Song S. SupplyNet: Supporting visual exploratory learning in supply chain via contextual multi-agent simulation. Visual Informatics. 2026:100345. doi:10.1016/j.visinf.2026.100345
BibTeX
@article{Li2026,
author = {Li, Yanjia and Han, Kelcy Kexin and Hu, Tianrui and Cao, Yi-Fan and Qu, Huamin and Song, Sicheng},
title = {SupplyNet: Supporting visual exploratory learning in supply chain via contextual multi-agent simulation},
journal = {Visual Informatics},
year = {2026},
pages = {100345},
doi = {10.1016/j.visinf.2026.100345}
}
EUVIMED