Abstract: An optimized multi-Agent negotiation model is built in order to make the Agent negotiations quick.Based on this model，a negotiation learning algorithm that considers the fairness of both negotiators is introduced.This algorithm evaluates offers from the opponent Agent based on the satisfaction degree，learning online to get the opponent’s knowledge from interactive instances of history and negotiation of this time，making concessions dynamically based on fair object.Through building the trading negotiation simulation model，it can validate the astringency of this algorithm.The result shows the model based on this algorithm is high efficient and fair.

摘要： 为了能够快速、高效地进行Agent协商，构建一个优化的多Agent协商模型。在这个模型的基础上，提出了一个基于协商各方公平性的协商学习算法。算法采用基于满意度的思想评估协商对手的提议，根据对方Agent协商历史及本次协商交互信息，通过在线学习机制预测对方Agent协商策略，动态得出协商妥协度并向对方提出还价提议。最后，通过买卖协商仿真实验验证了该算法的收敛性，表明基于该算法的模型工作的高效性、公平性。