A multi-agent system for e-commerce sellers whose catalogues are too large to watch by hand. It keeps an eye on competing marketplaces, recommends repricing moves and can apply them automatically. What it targets is the margin that quietly bleeds away while pricing and risk decisions lag behind what the market is already doing.
The award name states the axis outright. Winning a multi-agent category implies the judges looked at the division of labour itself — monitoring, recommending, applying — split across actors rather than bundled into one model call. Repricing is a domain where the cost of a late decision compounds, so there is a clear reason to keep agents watching. Letting a seller stop at recommendations or hand over execution is a practical answer to the unease of automated pricing.
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).