AutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms

arXiv:2610.16232v1 Announce Type: new Abstract: In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit model-specific artifacts and fail to generalize to independent models. Recent studies have shown that not all designers generalize equally well to independent models. In this work, we use agentic program search to iteratively propose, execute, evaluate, and revise code for nucleic-acid designers. We describe the successful strategies used to prompt the search. AutoNovo designers achieved the best observed mean among the evaluated methods on 3/3 DNA-design tasks in terms of in-silico performance, and 6/6 transfer tasks in terms of independent models. The designers come from a family of discovered nucleic acid designers rather than a single universal best designer. We plan to release the resulting designers. These results are the first steps in creating nucleic acid designers that maximize cross-model generalization, and thus improving the odds that in-silico designed sequences reflect real biology.

Related

• Active Learning Guided Design Space Refinement for Scalable Multi-Objective Bayesian Optimization in Materials Discovery
• Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
• Agentic High-Dimensional Bayesian Optimization with Hypothesis- and Evidence-Guided Search

Source: arXiv cs.LG | 2026-10-14