Google Research· Research

Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence

Rui Meng, Research Scientist, and Tomas Pfister, Director, Google Cloud Introducing the Science One Framework, an experimental research prototype designed to eliminate hallucinations by natively building verifiable evidence chains, and CoE Audit, an automated protocol to evaluate the integrity of AI-generated papers. Quick links Paper Share Copy link × Large language models (LLMs) are increasingly being deployed not just as coding assistants but as autonomous agents capable of conducting end-to-end scientific research workflows. Recent systems (e.g., Sakana’s AI-Scientist , AutoResearchClaw , DeepScientist , AI-Researcher ) can review literature, formulate hypotheses, execute experiments and write complete manuscripts that are comparable to human-authored papers. However, as the surface-level quality of these AI-generated manuscripts improves, a critical structural problem has emerged: verifiability. Because current autonomous research pipelines generate text iteratively, errors introduced at any stage are amplified. Some existing systems can generate …

Announced

30 Jul 2026 20:36 UTC