Scalable Complex Contract Negotiation with Structured Search and Agenda Management

Abstract

A large number of interdependent issues in complex contract negotiation poses a significant challenge for current approaches, which becomes even more apparent when negotiation problems scale up. To address this challenge, we present a structured anytime search process with an agenda management mechanism using a hierarchical negotiation model, where agents search at various levels during the negotiation with the guidance of a mediator. This structured negotiation process increases computational efficiency, making negotiations scalable for large number of interdependent issues. To validate the contributions of our approach, 1) we developed our proposed negotiation model using a hierarchical problem structure and a constraint-based preference model for real-world applications; 2) we defined a scenario matrix to capture various characteristics of negotiation scenarios and developed a scenario generator that produces test cases according to this matrix; and 3) we performed an extensive set of experiments to study the performance of this structured negotiation protocol and the influence of different scenario parameters, and investigated the Pareto efficiency and social welfare optimality of the negotiation outcomes. The experimental result supports the hypothesis that this hierarchical negotiation approach greatly improves scalability with the complexity of the negotiation scenarios.

RETRACTED: A bilateral negotiation model of complex contract based on negotiator’s utility information protection

“…Recently, some methods for solving nonlinear multi-attribute negotiation are proposed. Zhang et al 3 used scalable search and agenda management to study scalable complex contract negotiations. Jonge and Sierra 4 proposed a multilateral negotiation algorithm that is developed in a large nonlinear protocol space with limited time.…”

Divide-and-Conquer in Automated Negotiations Through Utility Decomposition

“…Future investigations will firstly focus on us-ing different agents and then running the simulations with different domains. Our approach also sets the basis for the possibility to combine our divide-and-conquer protocol with meta-negotiations, which as some related applications in many do-mains [22,25,28].…”