Accelerating Scientific Research with Gemini in the Real-World

Published
Source
arXiv
Paper number
1027
Field
AI / General
arXiv ID
2608.26701

Key points

  • Connected to CVD synthesis equipment, it designed an MXene synthesis route using harmless precursors and grew monolayer MoS2, MoSe2, and WS2 on the first attempt.
  • It built an agent for predicting E. coli colony morphology and produced results that quantitatively matched unpublished wet-lab measurements.
  • It fully autonomously designed a medical-response agent that outperformed 6 frontier models on HealthBench Hard/Professional.
  • Through 450 double-blind reviews by 30 experts, it demonstrated the effectiveness of a reliability module that reduces hallucinations and plagiarism in generated papers.
  • It showed that adaptive autonomy, which adjusts the level of human-AI collaboration by domain, is a key design dimension of closed-loop research.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)