DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design

arXiv:2610.13116 · cs.AI · Submitted 2026-10-09 · Read on arXiv

cs.AI

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/drylab-bio/DRYLAB-Bench

Terminology

• Benchmarking — 1× in this paper · explained in 4 episodes

Sources

• Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models II: Benchmark Generation Process
• Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
• Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools
• Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark
• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
• ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
• BioTIER: A Refusal Benchmark for Targeted Biological Risk Mitigation
• BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology
• RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems