Benchmarking and behavioral characterization of LLM agents for protein design

Abstract excerpt

Large language models (LLMs) are increasingly deployed as agents for scientific discovery, but standardized frameworks for evaluating their performance and behavior in scientific workflows are lacking. Protein design provides a demanding test case because modern workflows combine stochastic generative models, structure prediction systems, and physics-based evaluation tools that require extensive candidate explorat...

Topics

Open a Topic to create a Post that cites this publication.

• Algorithms
• Amino Acid Sequence
• Antibodies
• Antigens
• Computational Biology
• Neural Networks, Computer
• Protein Engineering
• Proteins

Identifiers and source

Literature Corpus work

1840f4ca-f7e4-5816-8221-e9a0e6363b21

DOI

10.64898/2026.05.06.723381