Sage-Taiyi 元认知架构登顶 Taiyi-Bench 科学构思评测
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
搞 AI for Science 的朋友可以看看这篇。它不是又一个只会生成论文点子的系统，而是在 Taiyi-Bench 上全面超过 AI Scientist-v2，还把提案真做进了实验室，钴催化反应产率从痕量提到 84%。做科研自动化或智能体架构的都值得对比一下它的元认知设计。
研究团队发布 Sage-Taiyi，一种受元认知启发的 AI 科学发现架构。在 Taiyi-Bench 上——一个包含来自 50 篇论文、十个学科共 265 个任务的 AI 科学家构思基准——Sage-Taiyi 在历史再发现与开放式构思全部八项指标上排名第一，总分 54.0，超过最强基线 AI Scientist-v2 的 47.9。
其核心机制是对证据、假设和未解决问题进行显式监控与控制：系统不断修正自身对研究状态的理解，据此调整研究目标，并选择可复用的推理方法来决定下一步研究什么、怎么研究。这种自评估闭环让构思过程不再是一次性生成，而是持续迭代的科学推理。
在五个专家指导的实际合作中，该系统的提案进入化学、材料科学与工程领域的实验与计算验证。化学方向上，反应条件优化将钴催化羰基化反应产率从痕量提升到 84%，光催化烯丙基胺化从 13% 提升到 69%。团队同时在两个外部科学构思基准上验证了性能。
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
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.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：Sage-Taiyi、AI Scientist-v2、Taiyi-Bench、智能体，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Weida Wang, Benteng Chen, Yigeng Jiang, Shuchen Pu, Weiping Shen, Zichao Liu, Yulin Su, Zitong Wang, Siyu Zhou, Zifu Wang, Yizhi Li, Xin Zong, Yuning Yang, Jixiang Bi, Yuan Wang, Chuyi Peng, Shiyao Geng, Qi Zhang, Kuan Lu, Mengzhu Li, Weiwang Xu, Peishan Xiang, Chengjun Liu, Chengrui Wei, Fangchen Yu, Shengji Tang, Yichen Jiang, Jingqi Ye, Cheng Yang, Tao Hu, Jianbiao Mei, Qinglong Cao, Kun Li, Yixin Chen, Shengyuan Xu, Juncheng Xiao, Yiheng Wang, Ruizhe Chen, Shiyang Feng, Runmin Ma, Xiangchao Yan, Zongsheng Cao, Haomeng Hu, Yu Ke, Taihui Wu, Meng Dai, Xu Guo, Haoyang Peng, Yinglong Ni, Pingsen Shi, Xiaosong Wang, Shuyue Hu, Haijun Li, Sherry Dongqi Bao, Yang Yang, Chao Yang, Jie Hou, Tianfan Fu, Yi Gong, Jin Zeng, Mao Su, Hongxia Hao, Fanyang Mo, Fenghua Ling, Tianshu Yu, Yunqi Cai, Baihong Chi, Jingwei Wang, Lei Wang, Chuncheng Bu, Shide Lv, Guangyu Wang, Yuqiang Li, Chunfeng Song, Lei Bai, Hui Wang, Xujun Fu, Li Cao, Lei Chen, Dahua Lin, Xing Xie, Bowen Zhou, Wenlong Zhang, Pinlong Cai, Peng Ye, Aiwen Lei, Jie Li, Shengchun Wang, Bo Zhang, Shufei Zhang），经 AITOP 多维评分管线结构化提炼。