[Paper] ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
Source: arXiv - 2606.11150v1
Overview
Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data. Increasingly, LLM agents can also perform in silico biology tasks that previously required experienced human biologists. These emerging AI capabilities offer new opportunities for scientific discovery and biomedical advances, but they also shift the landscape of biosecurity risks. To address this, we introduce the Agentic Bio-Capabilities Benchmark (ABC-Bench), a suite of tasks to measure agentic biosecurity-relevant capabilities. ABC-Bench evaluates LLM agents on both benign and dual-use biology tasks: writing code to operate liquid handling robots, designing DNA fragments for in vitro assembly, and evading DNA synthesis screening. These tasks require a combination of biology and software expertise. All tested LLM agents outperformed the median expert human baseliner on all three tasks. Agents performed highly on tasks drawing on published knowledge and well-documented protocols, and more weakly on a task requiring novel bioinformatics reasoning. In three wet-lab validation experiments, we found that OpenAI’s o4-mini-high produced scripts that, when run on an OpenTrons liquid handling robot, successfully assembled DNA with expected sequences.
Key Contributions
This paper presents research in the following areas:
- cs.AI
- cs.CY
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.AI.
Authors
- Andrew Bo Liu
- Samira Nedungadi
- Bryce Cai
- Alex Kleinman
- Harmon Bhasin
- Seth Donoughe
Paper Information
- arXiv ID: 2606.11150v1
- Categories: cs.AI, cs.CY
- Published: June 9, 2026
- PDF: Download PDF