NanoProteinLM: Towards Hill-Climbable Protein Language Model Research

Agentic autoresearch could extend recursive self-improvement to scientific discovery. Given an objective, an agent that proposes a change, tests it, keeps what works and repeats could explore a design space far larger than any group can cover by hand. Handing a real scientific question to such a loop, however, seldom returns anything useful, usually because the setting around the question was never configured for a closed loop. We ask what makes a research task hill-climbable, propose the ingredients an environment needs, and apply them to protein language-model training. The result is NanoProteinLM, an open and fully automatable environment with a public decontaminated corpus, a readable trainer, frozen evaluations and an explicit autoresearch protocol. Inside it, a simple sequential hill-climber discovers training recipes that beat a strong ESMC baseline and keep paying when retrained at substantially larger budgets; once the environment was well defined, no further search machinery was needed. We interpret the four changes that were kept and report why the others were dropped. We also share the lessons we learned in making the environment hill-climbable. Our contribution for the science community is twofold: Protein researchers gain an open recipe they can rerun and improve, and agent researchers gain a benchmark in which their progress returns directly to that recipe. All data and code will be open-sourced.