Auction-based agent negotiation via programmable tuple spaces

Auctions are proposed as a distributed negotiation mean, particularly useful in multiagent systems where both cooperative and self-interested agents compete for resources and services. The aim of this paper is to show how auction mechanisms on the Internet can be easily implemented by using programmable tuple spaces. Tuple spaces are shared repositories of information that follow the Linda model; the addition of programmability permits to adapt the tuple space behaviour to the application-specific requirements via reactions. In the implementation of auctions, programmable reactivity is exploited to uncouple the actual auction mechanisms from the selling and bidding policies of the attending agents.