Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks. Protein design provides a natural testbed: although machine learning (ML) methods achieve strong results, these are largely restricted to canonical amino acids and narrow objectives, leaving unfilled need for a generalist tool for broad design pipelines. We introduce Agent Rosetta, an LLM agent paired with a structured environment for operating Rosetta, the leading physics-based heteropolymer design software, capable of modeling non-canonical building blocks and geometries. Agent Rosetta iteratively refines designs to achieve user-defined objectives, combining LLM reasoning with Rosetta's generality. We evaluate Agent Rosetta on design with canonical amino acids, matching specialized models and expert baselines, and with non-canonical residues -- where ML approaches fail -- achieving comparable performance. Critically, prompt engineering alone often fails to generate Rosetta actions, demonstrating that environment design is essential for integrating LLM agents with specialized software. Our results show that properly designed environments enable LLM agents to make scientific software accessible while matching specialized tools and human experts.

翻译：大型语言模型（LLM）能够模拟推理并使用工具，为执行复杂科学任务的自主智能体创造了机遇。蛋白质设计提供了一个天然的试验场：尽管机器学习（ML）方法取得了显著成果，但这些方法主要局限于标准氨基酸和狭窄目标，对通用型设计工具的需求仍未得到满足。我们提出Agent Rosetta——一种配备结构化环境以操作Rosetta（领先的基于物理学的异聚合物设计软件，能够建模非标准构建模块和几何结构）的LLM智能体。Agent Rosetta通过结合LLM推理与Rosetta的通用性，迭代优化设计以实现用户定义的目标。我们在标准氨基酸设计任务上评估了Agent Rosetta，其表现与专用模型及专家基线相当；在ML方法无法处理的非标准残基设计任务中，也取得了可比性能。关键的是，单纯依靠提示工程通常无法生成Rosetta操作指令，这表明环境设计对于将LLM智能体与专业软件集成至关重要。我们的研究结果表明，设计得当的环境能使LLM智能体在匹配专业工具和人类专家水平的同时，进一步降低专业科学软件的使用门槛。