Purely Agent-Driven Black-Box Optimization for Biological Design

TL;DR

PABLO is a novel agent-driven, language-based optimization system that leverages scientific LLMs for biological design, achieving state-of-the-art results in molecular and peptide optimization tasks.

Contribution

The paper introduces PABLO, a hierarchical agentic system that uses pretrained scientific LLMs for iterative biological candidate refinement, surpassing existing methods in efficiency and effectiveness.

Findings

PABLO achieves state-of-the-art performance on molecular and peptide design tasks.

PABLO improves sample efficiency and final objective values over baselines.

Peptides optimized by PABLO showed strong activity against drug-resistant pathogens.

Abstract

Many key challenges in biological design -- such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering -- can be framed as black-box optimization over vast, complex structured spaces. Existing methods rely mainly on raw structural data and struggle to exploit the rich scientific literature. While large language models (LLMs) have been added to these pipelines, they have been confined to narrow roles within structure-centered optimizers. We instead cast biological black-box optimization as an agent-driven, language-based reasoning process. We introduce Purely Agent-driven BLack-box Optimization (PABLO), a hierarchical agentic system that uses scientific LLMs pretrained on chemistry and biology literature to generate and iteratively refine biological candidates. On both the standard GuacaMol molecular design and antimicrobial peptide optimization tasks, PABLO achieves state-of-the-art performance, substantially improving sample efficiency and final objective values over established baselines. Compared to prior optimization methods that incorporate LLMs, PABLO achieves competitive token usage per run despite relying on LLMs throughout the optimization loop. Beyond raw performance, the agentic formulation offers key advantages for realistic design: it naturally incorporates semantic task descriptions, retrieval-augmented domain knowledge, and complex constraints. In follow-up in vitro validation, PABLO-optimized peptides showed strong activity against drug-resistant pathogens, underscoring the practical potential of PABLO for therapeutic discovery.