Software agents are flexible, autonomous, and dynamic computational entities. For B2C e-commerce applications, the wide variety of choices to the consumers has also introduced the problem of information overloading. Meanwhile, there are so many e-shops and products for the consumers that it has become too time-consuming to find the best deal. In this paper, we present PumaMart, a Parallel and autonomous agents based Internet Marketplace, which deploys several novel models to facilitate autonomous and automatic online buying and selling by software agents (stationary and mobile) while providing fast response to consumers. These techniques include a 2-phase evaluation model, a parallel dispatch model and an auction-like negotiation model. Both evaluation model and negotiation model are based on the fuzzy evaluation criterion with clustering based grading function. What a consumer needs to do is to submit requests including the information for the desired products, selection preferences, through a web page in a Java-enabled browser. These information will be sent to the master agent at the server of the Agent Service Provider (ASP), which will employ its worker agents for subsequent shop searching/filtering, offer gathering/evaluating, negotiating, even booking and payment.