In existing e-marketplaces, buyers can use search engines to find products that exactly match their demands, but some products those are potentially interesting to them cannot be found out. This research aims to design a multi-agent e-marketplace in which buyers and sellers can delegate their agents to argue over product attributes via an agent-to-agent argumentation mechanism. A seller agent is able to persuade a buyer agent to believe the seller’s product is interesting to the buyer. To make this idea possible, this research adopts the Semantic Web technology to express agents’ ontologies and uses an abstract argumentation framework with dialectical game approach to support defeasible reasoning. This research hopes the proposed architecture and approach can help buyers to find out potential interesting products and help sellers to increase revenue through their agents and help existing and initiative e-marketplaces to design their argumentation mechanisms.