Developing T cell receptors (TCRs) with sufficiently high affinity for tumor antigens (TAs) remains a fundamental challenge in TCR-T immunotherapy. Experimental methods such as affinity maturation and high-throughput screening have enabled the identification of TCRs with enhanced activity, but the efficiency of such methods is limited by throughput, coverage, and the generally lower affinities of naturally occurring TCRs towards TAs. To address these challenges, we present TCRPPO2, an integrated AI-driven, in silico affinity maturation model for peptide-specific TCR optimization. Using reinforcement learning, TCRPPO2 learns mutation policies that iteratively enhance the objective of the TCR binding affinity towards the target peptide, derived from predictive models trained on carefully curated interaction data. The model is further augmented by a generative AI critic model that discourages implausible designs to ensure the validity. The designs are further screened by robust post-screening methods that leverage diverse functional annotations and physical prior knowledge. We applied TCRPPO2 to the clinically relevant MART-1 antigen and experimentally validated the designed candidates in Jurkat cell-based functional assays. Among the five engineered TCRs all demonstrating positive cellular responses, three showed significantly increased activities relative to their templates and one with pronounced enhancement. These functional gains were consistent with improved interaction energy from structural and physical modeling. Together, our results support a generalizable paradigm for TCR engineering, in which learned mutation policies can efficiently navigate the peptide-specific binding landscape of TCRs and propose biologically enhanced candidates without explicit structural