mlsanityData to 14 Oct 2026

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

arXiv 2604.16896 ↗First posted 18 Apr 2026q-bio.QM cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

16 of 46 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  7. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  8. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  9. 2023A Text-guided Protein Design Frameworkcited by 64
  10. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Startcited by 41
  11. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 33
  12. 2025Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discoverycited by 12
4 more
  1. 2024Annotation-guided Protein Design with Multi-Level Domain Alignmentcited by 9
  2. 2024EvoLlama: Enhancing LLMs' Understanding of Proteins via Multimodal Structure and Sequence Representationscited by 9
  3. 2025Protein Design with Dynamic Protein Vocabularycited by 5
  4. 2025PDFBench: A Benchmark for De novo Protein Design from Functioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Promptscited by 1
  2. 2026Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Designcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
  2. 2025Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation
  3. 2025Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
  4. 2026Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools
  5. 2024TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering
  6. 2026AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
  7. 2025Steering Protein Language Models
  8. 2026Proteo-R1: Reasoning Foundation Models for De Novo Protein Design