What AI scientists may be missing is the ability to know what they don't know.
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
🔭 Overview
An architecture that adds a metacognitive layer to a scientific-discovery AI, monitoring and controlling the search itself.
🧩 The problem
Earlier AI scientist systems fail to retain findings, evidence and applicability conditions across search branches. They can overlook shared dependencies and past failures, and overreact to recent outcomes.
⚙️ The approach
・The search side has a Target Tree (question decomposition), an Idea Graph (idea lineage) and an Evidence State (sourced evidence)
・The regulation side keeps a Cognitive State of current understanding and uncertainty, and picks next moves from ten heuristics
🧪 Results
On the authors' own Taiyi-Bench (265 tasks, 10 disciplines) it scores 54.0 overall vs 47.9 for the strongest baseline, AI Scientist-v2, with a 66.3% pairwise win rate.
🔬 Use cases
In five expert-collaborative cases, for example, a photocatalytic allylic amination yield rose from 13% to 69%. Note that scoring relies on the same authors' benchmark and an LLM verifier, and the cases are individual examples.
#
AIScientist# #
Metacognition#