International Automated Negotiating Agents Competition (ANAC) was held in conjunction with International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS). This competition brings together researchers from the negotiation community and provides a unique benchmark for evaluating practical negotiation strategies in multi-issue domains. The previous competitions have provided the novel ideas in the field of autonomous agent design. Recently, the focus of the competition is interleaving learning with negotiation strategies. In this paper, we propose AgentKF which estimates the opponent's strategies based on the past negotiation sessions. Our agent tries to compromise to the estimated maximum utility of the opponent by the end of the negotiation. In addition, our agent can adjust the speed of compromising and search the pareto frontier using past negotiation sessions. Our agent won the 1st prize in the qualifying round of ANAC-2013.