Google Introduces Two AI Agents for Scientific Research: PaperVizAgent for Illustrations and ScholarPeer for Reviewing

Google Research introduced PaperVizAgent and ScholarPeer, two AI agents to streamline academic research. PaperVizAgent is an autonomous framework that creates academic illustrations from text by orchestrating five specialized agents: retriever, planner, stylist, visualizer, and critic. Evaluations show it outperforms baselines like GPT-Image-1.5 and Paper2Any, achieving an overall score of 60.2 versus a human baseline of 50.0. ScholarPeer is a multi-agent framework for automated peer review that uses a sub-domain historian agent, baseline scout, and multi-aspect Q&A engine to produce literature-grounded reviews. In tests, it achieved significant win-rates against state-of-the-art automated reviewers and reduced the gap to human-level diversity. Both agents are experimental prototypes and not production-ready.