analiza aiqbench
This study demonstrates how LLM agents can effectively interface with specialized physics-based software like Rosetta to solve protein design problems beyond the reach of current pure ML models. The research highlights that successful integration requires structured environment designs rather than relying solely on prompt engineering, bridging a gap between generalist AI reasoning and domain-specific scientific tools.
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
arXiv:2603.15952v2 Announce Type: replace 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2603.15952 [cs.AI]
(or arXiv:2603.15952v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2603.15952 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 268 cuvinte
Subiecte conexe
Assessing Language Models for Scientific Applications: Inertial Confinement Fusion as a Use Case
arXiv · 31 oct. 2026
PAPERBENCHX: Can AI Reproduce Science Across Disciplines?
arXiv · 31 oct. 2026
MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities
arXiv · 28 iul. 2026
Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
arXiv · 17 sept. 2026