A Rule-Driven Approach for Defining the Behaviour of Negotiating Software Agents

One problem with existing agent-mediated negotiation systems is that they rely on ad hoc, static, non-adaptive, and hardcoded schemes to represent the behavior of agents. This limitation is probably due to the complexity of the negotiation task itself. Indeed, while negotiating, software (human) agents face tough decisions. These decisions are based not only on the information made available by the negotiation server, but on the behavior of the other participants in the negotiation process as well. The information and the behavior in question are constantly changing and highly uncertain. In this paper, we propose a ruledriven approach to represent, manage and explore negotiation strategies and coordination information. Among the many advantages of this solution, we can cite the high level of abstraction, the closeness to human understanding, the versatility, and the possibility to modify the agents’ behavior during the negotiation. To validate our approach, we ran several agent tournaments, and used a rule-driven mechanism to implement bidding strategies that are common in the English and Dutch auctions. We also implemented simple coordination schemes across several auctions. The ongoing validation work is detailed and discussed in the second part of the paper.