The importance of the epidermal growth factor receptor (EGFR) axis in tumorigenesis and tumor progression makes it an attractive target for the development of anticancer therapies. Strategies aimed at inhibiting the EGFR pathway included different classes of compounds, with monoclonal antibodies and tyrosine kinase inhibitors being the most widely-investigated agents in colorectal cancer. Although anti-EGFR therapies are active in some patients, disease will become refractory to therapy in nearly all patients. Identification of specific markers likely to predict which patients will best respond to anti-EGFR therapy is a major challenge. While the occurrence of rash is associated with greater likelihood of response, EGFR staining by immunohistochemistry at baseline is not. Among biological predictors, some studies indicate that activated EGFR, EGFR amplification, absence of KRAS mutations, PTEN expression, and low VEGFR expression are implicated in response to anti-EGFR monoclonal antibodies. Moreover, germinal gene polymorphisms, such as dinucleotide repeats polymorphism or FcgammaR polymorphism, have been shown to be associated with response to anti-EGFR therapy. Since most available data come from retrospective studies, there is a need to validate these results in prospective trials.