🧲🧲 Google AI Introduces PlanGEN: A Multi-Agent AI Framework Designed to Enhance Planning and Reasoning in LLMs through Constraint-Guided Iterative Verification and Adaptive Algorithm Selection
Researchers from Google Cloud AI Research, Google Research, Google DeepMind, Houston Methodist, Sequome, Fleming Initiative and Imperial College London, and Stanford University School of Medicine have proposed an AI co-scientist, a multi-agent system built on Gemini 2.0 designed to accelerate scientific discovery. It aims to uncover new knowledge and generate novel research hypotheses aligned with scientist-provided objectives. Using a “generate, debate, and evolve” approach, the AI co-scientist uses test-time compute scaling to improve hypothesis generation. Moreover, it focuses on three biomedical domains: drug repurposing, novel target discovery, and explanation of bacterial evolution mechanisms. Automated evaluations show that increased test-time computation consistently improves hypothesis quality.…..