A key issue in the design of Belief-Desires-Intentions (BDI) agents is that of fnding an appropriate strategy for Intention Reconsider- ation (IR). Traditional approaches to IR defi nes the policy in the agent's design stage, which makes impossible to modify it in execution time. This is clearly not a practical solution for agents operating in dynamic and changing environments. Besides, IR typically involves considering multi- ple criteria. That is why, in this work, we propose a novel approach to IR based on a dichotomous choice model. This approach allows changing commitments to intentions depending on how the environment evolves and involves multi-criteria aggregation for IR.