Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation

TL;DR

This paper introduces a decentralized swarm intelligence framework using multiple large language model agents for de novo protein design, validated experimentally, offering a flexible, scalable, and efficient alternative to existing methods.

Contribution

The paper presents a novel agent-based, decentralized LLM framework for protein design that operates without fine-tuning, enabling diverse sequence generation with emergent behaviors.

Findings

Achieves efficient, objective-directed protein design within a few GPU-hours.

Operates without fine-tuning or specialized training, demonstrating scalability.

Validated with experiments on alpha helix and coil proteins.

Abstract

Designing proteins de novo with tailored structural, physicochemical, and functional properties remains a grand challenge in biotechnology, medicine, and materials science, due to the vastness of sequence space and the complex coupling between sequence, structure, and function. Current state-of-the-art generative methods, such as protein language models (PLMs) and diffusion-based architectures, often require extensive fine-tuning, task-specific data, or model reconfiguration to support objective-directed design, thereby limiting their flexibility and scalability. To overcome these limitations, we present a decentralized, agent-based framework inspired by swarm intelligence for de novo protein design. In this approach, multiple large language model (LLM) agents operate in parallel, each assigned to a specific residue position. These agents iteratively propose context-aware mutations by integrating design objectives, local neighborhood interactions, and memory and feedback from previous iterations. This position-wise, decentralized coordination enables emergent design of diverse, well-defined sequences without reliance on motif scaffolds or multiple sequence alignments, validated with experiments on proteins with alpha helix and coil structures. Through analyses of residue conservation, structure-based metrics, and sequence convergence and embeddings, we demonstrate that the framework exhibits emergent behaviors and effective navigation of the protein fitness landscape. Our method achieves efficient, objective-directed designs within a few GPU-hours and operates entirely without fine-tuning or specialized training, offering a generalizable and adaptable solution for protein design. Beyond proteins, the approach lays the groundwork for collective LLM-driven design across biomolecular systems and other scientific discovery tasks.