Today for AI
HOT RADAR
industryHEAT 9.9°

AI CURATED HOT STORY · 11/9/2026

First Wet-Lab Closed-Loop Benchmark AISLE Debuts for AI Scientists

1 reports archived1 independent sourcesupdated 11/9/2026, 16:45:00
Synthesis & Latest Updates
1 Sources Cross-Validated

MasterAI-EAM, together with several top research institutions, launched AI Scientists' Last Exam (AISLE), billed as the first public benchmark for closed-loop dry-and-wet-lab scientific discovery, letting different models be tested under unified standards in real physical experiments. It aims to fill the long-missing reproducible, comparable physical verification layer in AI for Science, using nature itself as the verifier.

LATEST/MasterAI-EAM, together with several top research institutions, launched AI Scientists' Last Exam (AISLE), billed as the first public benchmark for closed-loop dry-and-wet-lab scientific discovery, letting different models be tested under unified standards in real physical experiments. It aims to fill the long-missing reproducible, comparable physical verification layer in AI for Science, using nature itself as the verifier.

Hourly heat curve

10 fully observed hours
Now
9.9
Peak
11.917:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. 机器之心 (微信公众号)T2·72 pts

    First Wet-Lab Closed-Loop Benchmark AISLE Debuts for AI Scientists

    • AISLE is the first public benchmark for closed-loop dry-and-wet-lab scientific discovery, emphasizing real physical validation over purely virtual inference
    • It targets the cross-lab incomparability caused by equipment differences, execution error and cost
    • Code and paper are open-sourced, offering a unified standard to compare models' experimental capability