We used ProtRL to fine-tune ZymCTRL on 600 EGFR-related sequences (BLAST‐retrieved with wild-type EGF), generating 10,000 candidates and filtered them by perplexity and length (FT method). Six designs were tested experimentally in round 1 (coinciding with round 2 of the Protein Design Competition), yielding three binders with affinities of 328–819 nM. We then applied DPO (RL method), using measured Kd, sequence length, TM-score, and expression level as reward components.