Leash Bio Releases Minos Scientific Reasoning Dataset
Understand the story
Leash Bio's Ian Quigley explained on the Latent Space podcast the company's computational-speed "lab-in-the-loop" system: using DNA-encoded library (DEL) technology to generate high-throughput protein–small molecule interaction data, and training the Hermes model on it, which—using only the company's own data—matches Boltz on public benchmarks. Along the way, the team discovered tens of thousands of "lab-in-the-loop" simulated data points. These developed into the Minos project within two months. On October 15, 2026, Leash Bio released Minos as a preprint, blog post, and open dataset, positioned as a reinforcement learning resource for AI agents to perform verifiable scientific reasoning.
AI overview of reporting · Updated 4 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Latent SpaceLab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio
On a podcast, Leash Bio's Ian Quigley explained how its DNA-encoded library (DEL) technology tames high-throughput protein-small-molecule interaction data and trained the Hermes model, which matches Boltz on public benchmarks using only the company's own data. The team also uncovered tens of thousands of lab-in-the-loop simulation data points, grew into Minos within two months, and today released a preprint, blog post, and open dataset for reinforcement learning where AI agents do verifiable scientific reasoning.
Story heat trend
Current heat3·Comparable peak10（10/15 06:00）·Comparable change over 24 hours -51%
The trend compares the same continuously observed sources, which may cover fewer sources than the current heat score. Hover or select the chart to inspect each hour; use the left and right arrow keys to navigate.