Negotiating Agents

Abstract

Negotiation is a complex emotional decision-making process aiming to reach an agreement to exchange goods or services. From an agent technological perspective creating negotiating agents that can support humans with their negotiations is an interesting challenge. Already more than a decade, negotiating agents can outperform human beings (in terms of deal optimality) if the negotiation space is well-understood. However, the inherent semantic problem and the emotional issues involved make that negotiation cannot be handled by artificial intelligence alone, and a human-machine collaborative system is required. This article presents research goals, challenges, and an approach to create the next generation of negotiation support agents.

Methods to Analyze Negotiation Processes

“…With the rise of new technologies, the Internet and social media applications we have witnessed a disruptive change: negotiations have expanded into the virtual world and now can be conducted virtually anytime and anywhere, across geographical and temporal distances. The technological innovations have not only triggered the online/offline debate and whether or how computer-mediated negotiations may differ from face to face negotiations, but also allowed to support negotiators via specific systems and the development of artificial negotiation agents based on analytic models or heuristics to conduct bilateral, multi issue human-agent or agent-agent negotiations (see Jonker et al 2012). Yet, most recent developments in data-mining, machine learning, and artificial intelligence all have the potential for another potentially disruptive change in the area of negotiation support.…”

The AI Rebellion: Changing the Narrative

“…The ability to survive and thrive, while not strictly following commands at all times, is an essential part of AI autonomy, and is exemplified by agents that react to unexpected events, deviate from initial plans, exploit opportunities, formulate their own new goals, and are driven to explore and learn by intrinsic motivation (Vattam et al, 2013;Van Der Krogt and De Weerdt, 2005;Singh et al, 2010). AI explanation and negotiation skills, which are necessary to express a well-founded "no" in a convincing, prosocial manner, have also been studied (Molineaux and Aha, 2015;Jonker et al, 2012;Gratch, Nazari, and Johnson, 2016). Hence, although not explicitly advertising themselves as such, agents incorporating various aspects of rebellion already exist and are proving beneficial.…”

Human-Computer Interaction in E-Negotiation

“…The idea is to reach synergy between negotiation agents and humans, neutralizing each other's weaknesses and taking advantage of strengths. While humans can understand emotional tone and context of negotiation, they need support in neutralizing emotions and focusing on their interests (Jonker et al, 2012).…”