Can Social Agents Efficiently Perform in Automated Negotiation?

In the last few years, we witnessed a growing body of literature about automated negotiation. Mainly, negotiating agents are either purely self-driven by maximizing their utility function or assuming cooperative stance all parties involved in We argue that, while optimizing one’s is essential, society should not ignore opponent’s final agreement to improve agent’s long-term perspectives system. This article aims show whether it possible design social agent (i.e., one that optimize both sides’ functions) performing efficiently an society. Accordingly, propose supported portfolio strategies, novel tit-for-tat concession mechanism, and frequency-based opponent modeling mechanism capable adapting its behavior according state The results proposed only maximizes metrics such as distance Nash bargaining point Kalai but also shown be pure mixed equilibrium strategy some realistic societies.