Minos: premeasured experimental worlds for studying how AI agents do science
rbhar90 · x · 2026-10-20
The team released Minos, a framework for agentic science built around a "zero-latency lab-in-the-loop": real experiments are too slow for agents that need an act-observe-decide cycle.
How it works:
- Measure once: physically measure a molecule library (e.g., AMA020 with 1,021,880 molecules, Kin0b with 6,255,468)
- Build measured worlds: organize results into premeasured experimental spaces (e.g., 472 amines × 433 aldehydes, every cell a physically measured score)
- Agents explore: multiple models run repeated rollouts on the same world, proposing candidates, looking up measurements, and revising hypotheses
The authors stress Minos isn't meant to produce the best scientific results, but to understand how AI agents make scientific decisions and help them make better ones.
More from coding & agent
- Claude Code v2.1.304 adds guided auto-mode setup, stricter permissions and usage warnings — ashwin-ant · 2026-10-20
- Pixel: a library bringing 120 FPS graphical UIs with Chromium WebView to the terminal — aidenybai · 2026-10-20
- Swarms argues Collective Superintelligence (CSI) will surpass AGI and ASI — KyeGomezB · 2026-10-20
- AI is already doing real work in RF chip design, FPGA optimization and 3D CAD, engineers say — mark_k · 2026-10-20
- Code review isn't dead: half of large AI-generated diffs add requirements you don't have — rseroter · 2026-10-20
- Rule of thumb: spend 90% of your RL task compute on trying to break them — marktenenholtz · 2026-10-20