AI Safety and Regulation
July 30, 2026

Google introduces Science One for verifiable autonomous AI research

Google Research has introduced Science One, an experimental autonomous research framework that uses Chain-of-Evidence to eliminate hallucinated citations and produce verifiable, reproducible AI-generated scientific research.

Google Research has unveiled Science One, an experimental autonomous research framework designed to improve the reliability of AI-generated scientific research. Built around a new Chain-of-Evidence (CoE) framework, the system ensures every claim, citation, method, and reported result is linked to verifiable supporting evidence.

Google also introduced CoE Audit, an automated evaluation protocol that checks reference accuracy, method-code alignment, score reproducibility, and specification compliance.

In Google's evaluation, Science One achieved zero phantom references while outperforming existing autonomous research systems on verifiability and remaining competitive on research benchmarks such as MLE-Bench and Parameter-Golf.

#
Google

Read Our Content

See All Blogs
Gen AI

Top Anthropic consulting partners for Claude AI development in 2026

Deveshi Dabbawala

August 4, 2026
Read more
AI safety

Enterprise AI security: How GoML builds prompt injection-resistant applications

Paushigaa S

July 21, 2026
Read more