Impressive new work from Google DeepMind showing real-world applications of agents for scientific research.

Impressive new work from Google DeepMind showing real-world applications of agents for scientific research. Impressive new paper from Google DeepMind. (bookmark it) It takes Co-Scientist out of simulation and into real-world experiments. A summary of the results: In computer science, it found an inference-time scaling architecture that beat six frontier models on HealthBench Hard and P…

Related

• congrats on the launch! As the task horizons on agents gets longer, we need more work evaluating and training models to be better in long-ru…
• This is a wild result. Locus, the automated research system from @intology, post-trained Qwen3 base models that beat the official human-tune…
• Applying multimodal biological foundation models across therapeutics and patient care

Source: DAIR.AI (X) | 2026-08-28