ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design

TL;DR

ProtoCycle is a novel framework that uses language models and feedback-driven cycles to improve text-guided protein design, bridging the plan-execute gap with reflection and reinforcement learning.

Contribution

It introduces a reflective, tool-augmented planning framework for protein design that enhances sequence quality and language alignment over traditional methods.

Findings

ProtoCycle achieves strong language alignment.

It maintains competitive foldability.

Reflection significantly improves sequence quality.

Abstract

Designing proteins that satisfy natural language functional requirements is a central goal in protein engineering. A straightforward baseline is to fine-tune generic instruction-tuned LLMs as direct text-to-sequence generators, but this is data- and compute-hungry. With limited supervision, LLMs can produce coherent plans in text yet fail to reliably realize them as sequences. This plan-execute gap motivates ProtoCycle, an agentic framework for protein design that uses LLMs primarily to drive a multi-round, feedback-driven decision cycle. ProtoCycle couples an LLM planner with a lightweight tool environment designed to emulate the iterative workflow of human protein engineering and uses LLM-driven reflection on tool feedback to revise plans. Trained with supervised trajectories and online reinforcement learning, ProtoCycle achieves strong language alignment while maintaining competitive foldability, and ablations show that reflection substantially improves sequence quality.