AgentPLM equips pre-trained protein language models with reasoning-augmented decoding using tools such as ESMFold and FoldX plus contrastive agent policy optimization, reporting state-of-the-art gains on de novo enzyme, antibody, and thermostability tasks.
Rodriques , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
AgentPLM equips pre-trained protein language models with reasoning-augmented decoding using tools such as ESMFold and FoldX plus contrastive agent policy optimization, reporting state-of-the-art gains on de novo enzyme, antibody, and thermostability tasks.