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

2026-04-18

AI Summary

This work addresses the challenge that large language models (LLMs) struggle to reliably translate natural language functional specifications into foldable protein sequences under limited supervision. To bridge the gap between textual planning and sequence realization, the authors propose ProtoCycle, a framework that emulates the iterative design process of human protein engineers through a multi-round, feedback-driven decision loop. ProtoCycle integrates an LLM-based planner, lightweight protein design tools, and a reflection-based tool-augmentation mechanism. This approach simultaneously maintains high sequence foldability and significantly improves alignment with natural language requirements. Experimental results demonstrate that the incorporation of reflection effectively enhances the quality of generated sequences, and ablation studies further confirm the critical role of this mechanism in the overall pipeline.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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.

Problem

• protein design
• text-to-sequence generation
• plan-execution gap
• language alignment
• foldability

Innovation

• ProtoCycle
• tool-augmented planning
• reflective reasoning
• protein design
• language-aligned generation