Purely Agent-Driven Black-Box Optimization for Biological Design
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914538539974656 |
|---|---|
| author | Maus, Natalie Zeng, Yimeng Jones, Haydn Thomas Huang, Yining Goel, Gaurav Ng Rose, Alden Kim, Kyurae Lee, Hyun-Su Torres, Marcelo Der Torossian Wan, Fangping de la Fuente-Nunez, Cesar Yatskar, Mark Bastani, Osbert Gardner, Jacob R. |
| author_facet | Maus, Natalie Zeng, Yimeng Jones, Haydn Thomas Huang, Yining Goel, Gaurav Ng Rose, Alden Kim, Kyurae Lee, Hyun-Su Torres, Marcelo Der Torossian Wan, Fangping de la Fuente-Nunez, Cesar Yatskar, Mark Bastani, Osbert Gardner, Jacob R. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22382 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Purely Agent-Driven Black-Box Optimization for Biological Design Maus, Natalie Zeng, Yimeng Jones, Haydn Thomas Huang, Yining Goel, Gaurav Ng Rose, Alden Kim, Kyurae Lee, Hyun-Su Torres, Marcelo Der Torossian Wan, Fangping de la Fuente-Nunez, Cesar Yatskar, Mark Bastani, Osbert Gardner, Jacob R. Machine Learning 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. |
| title | Purely Agent-Driven Black-Box Optimization for Biological Design |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.22382 |