Zero-shot mutation prediction is vital for low-resource protein engineering, yet existing protein language models (PLMs) often yield statistically confident results that ignore fundamental biophysical constraints. Currently, selecting candidates for wet-lab validation relies on manual expert auditing of PLM outputs, a process that is inefficient, subjective, and highly dependent on domain expertise. To address this, we propose Rank-and-Reason (VenusRAR), a two-stage agentic framework to automate this workflow and maximize expected wet-lab fitness. In the Rank-Stage, a Computational Expert and Virtual Biologist aggregate a context-aware multi-modal ensemble, establishing a new Spearman correlation record of 0.551 (vs. 0.518) on ProteinGym. In the Reason-Stage, an agentic Expert Panel employs chain-of-thought reasoning to audit candidates against geometric and structural constraints, improving the Top-5 Hit Rate by up to 367% on ProteinGym-DMS99. The wet-lab validation on Cas12i3 nuclease further confirms the framework's efficacy, achieving a 46.7% positive rate and identifying two novel mutants with 4.23-fold and 5.05-fold activity improvements. Code and datasets are released on GitHub (https://github.com/ai4protein/VenusRAR/).
@article{arxiv.2602.00197,
title = {Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction},
author = {Yang Tan and Yuanxi Yu and Can Wu and Bozitao Zhong and Mingchen Li and Guisheng Fan and Jiankang Zhu and Yafeng Liang and Nanqing Dong and Liang Hong},
journal= {arXiv preprint arXiv:2602.00197},
year = {2026}
}