Agent behaviors in virtual negotiation environments

Abstract

A computational prototype of negotiation behavior is presented where the following occurs: (1) agents employ different concession matching tactics; (2) agents are unaware of opponent preferences; (3) agents incur a cost for delaying settlements; (4) agents vary in terms of goal difficulty and initial offer magnitude; and (5) demands and counter-offers are made and evaluated based on the opponent's degree of concession matching. This research explores the impact of the interaction of different agent behaviors on the negotiation process and the outcome of the negotiation. Simulation experiments show that the prototype is able to manifest fundamental patterns and confirms the effectiveness of classical negotiation and mediation strategies, such as ambitious goals and aggressive concession matching tactics. The model reveals some counterintuitive patterns that may shed a new perspective on the effects of time constraints and information availability.