AI Daybook
AI Daybook
오늘의 지면
논문연구·논문

Sage-Taiyi, 메타인지로 과학 발견을 안내하는 AI 시스템

Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

매체
Hugging Face
게시
중요도
3/5
화제 지수
19

한국어 요약

누적된 과학적 이해를 바탕으로 다음 조사 대상과 방법을 스스로 선택하는 메타인지 기반 아키텍처 Sage-Taiyi를 제안했다. 50개 논문 265개 과제를 담은 AI 공동 과학자 벤치마크 Taiyi-Bench에서 종합 점수 54.0으로 기존 최강 기준(AI Scientist-v2, 47.9)을 앞섰다. 화학에서 코발트 촉매 카보닐화 반응의 수율을 흔적 수준에서 84%로, 광촉매 알릴 아민화를 13%에서 69%로 높였다.

원문 발췌 · English

We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation benchmark comprising 265 tasks from 50 papers across ten disciplines, Sage-Taiyi ranks first on all eight metrics of historical rediscovery and open-ended ideation, achieving an Overall score of 54.0 compared with 47.9 for the strongest baseline, AI Scientist-v2. It also performs well on two external scientific ideation benchmarks. Five expert-guided collaborations further connect its proposals to experimental and computational validation across chemistry, materials science, and engineering. In chemistry, reaction-condition optimization raises the yield of cobalt-catalyzed carbonylation from trace amounts to 84% and photocatalytic allylic amination from 13% to 69%. These results support metacognitive regulation as an approach to scientific ideation and its progression toward practical validation.

#benchmark#metacognition#scientific discovery
원문 기사 읽기
전체 보기 →