Shanghai AI Laboratory (Weida Wang et al.) · Metacognitive Co-Scientist
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
Sage-Taiyi is a metacognition-inspired architecture that uses accumulated scientific understanding to choose what to investigate and how. On Taiyi-Bench, an AI co-scientist ideation benchmark of 265 tasks from 50 papers, it scores 54.0 Overall against 47.9 for the strongest baseline, AI Scientist-v2. In chemistry, its reaction-condition optimisation raised cobalt-catalysed carbonylation yield from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. The page does not state a licence or code release.
Open the source ↗Similar Research & Safety releases
- LongBanana
Kolors Team, Kuaishou Technology (Haoxiang Cao et al.) · Image Synthesis Benchmark · Week 47, 2026
- Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
George Ling, Shanshan Zhong, Lijin Yang, Hao Yang, Nanxiang Li, Zhongzhan Huang (Carnegie Mellon University) · Benchmark Compression · Week 46, 2026
- Dream-RSI
Google, DeepMind, Maryland & Virginia · Recursive Self-Improvement · Week 39, 2026
- WeatherNext 3
Google DeepMind · WeatherNext 3 · Week 36, 2026
- mdlARC
Mithil Vakde · Efficient ARC-AGI Model · Week 36, 2026
- WikiSkill
Tang, Rashtchian, Ferng, Tomkins, Juan and Vu · Skill Evolution · Week 36, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.