{"ID":2863167,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00352","arxiv_id":"2510.00352","title":"AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance","abstract":"Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce AReUReDi (Annealed Rectified Updates for Refining Discrete Flows), a discrete optimization algorithm with theoretical guarantees of convergence to the Pareto front. Building on Rectified Discrete Flows (ReDi), AReUReDi combines Tchebycheff scalarization, locally balanced proposals, and annealed Metropolis-Hastings updates to bias sampling toward Pareto-optimal states while preserving distributional invariance. Applied to peptide and SMILES sequence design, AReUReDi simultaneously optimizes up to five therapeutic properties (including affinity, solubility, hemolysis, half-life, and non-fouling) and outperforms both evolutionary and diffusion-based baselines. These results establish AReUReDi as a powerful, sequence-based framework for multi-property biomolecule generation.","short_abstract":"Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality...","url_abs":"https://arxiv.org/abs/2510.00352","url_pdf":"https://arxiv.org/pdf/2510.00352v2","authors":"[\"Tong Chen\",\"Yinuo Zhang\",\"Pranam Chatterjee\"]","published":"2025-09-30T23:33:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"q-bio.BM\"]","methods":"[\"Diffusion Model\"]","has_code":false}