UPDF AI

Agent-Guided Ranking Policy Improvement for Peptide Drug Candidate Prioritization

Edward Wijaya

2026 · DOI: 10.64898/2026.04.19.719536
bioRxiv · 0 Citations

TLDR

Across a public benchmark of 3,554 antimicrobial peptides scored on all four endpoints, the agent-derived policy captures 65% of the best candidates in its top-20 shortlist, compared to 44% for NSGA-II and 61% for both equal-weight scalarization and best-of-1,000 random weight search.