We propose a decision engine with QoS awareness that can automatically negotiate for the appropriate adaptation strategies to use to produce an optimal adapted version. The QoS-sensitive approach complements the lossy nature of the transcoding operations. The decision engine will look for the best tradeoff among various parameters in order to reduce the loss of quality in various domains. Quantitative methods are suggested to measure the QoS of the content versions. Based on the particular user perception of these quality domains and other context information on the client capability, the proposed negotiation algorithm will determine a content version with a good aggregate score. We study factors such as processing overhead and the optimization accuracy of the algorithm, and their tradeoff. We have built a prototype document adaptation system for PDF documents to demonstrate the viability of our approach.