Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

TL;DR

This paper presents Agent Rosetta, an LLM-based agent that integrates with Rosetta software to enable broad and flexible protein design, including non-canonical residues, matching expert performance.

Contribution

Introduction of Agent Rosetta, a novel LLM agent framework that interfaces with Rosetta to perform complex, broad-spectrum protein design tasks beyond canonical amino acids.

Findings

Agent Rosetta matches expert baselines in canonical amino acid design.

It successfully designs with non-canonical residues where ML approaches fail.

Proper environment design is crucial for integrating LLMs with scientific software.

Abstract

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.