Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
Abstract
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.
Figures & tables
| Methodological heuristic | Methodological role |
| Evidence-driven discovery | Construct explanations from observations, anomalies, or failed predictions, and identify subsequent tests [ 1 , 4 ] . |
| Model-driven discovery | Vary assumptions or conditions in a theory or model, derive new consequences, and examine their scope and testable predictions [ 23 ] . |
| Analogical transfer | Align the relational structures of source and target problems, and transfer mechanisms under target-domain constraints [ 24 , 25 ] . |
| Representation-driven reformulation | Reformulate entities, variables, or relations to open new solution paths, then map results back to the original problem [ 26 , 27 , 28 ] . |
| Compositional synthesis | Decompose a target into functions, select and integrate compatible components, and evaluate the resulting system [ 29 , 17 ] . |
| Inverse design | Infer conditions and subtargets from a required outcome, construct a design, and validate it through forward evaluation [ 3 ] . |
| System | Rediscovery | Open-ended | Overall | ||||||||
| Find. | Exact | Cover. | Look. | Avg. | Nov. | Effect. | Feas. | Div. | Avg. | ||
| Direct generation | |||||||||||
| GPT-5.6-Sol | 72.48 | 9.30 | 25.27 | 23.28 | 32.58 | 39.17 | 66.02 | 49.32 | 31.63 | 46.54 | 39.56 |
| Claude-Opus-5 | 72.32 | 8.02 | 23.35 | 21.34 | 31.26 | 42.66 | 58.18 | 45.78 | 28.70 | 43.83 | 37.54 |
| Gemini-3.7-Flash | 66.18 | 7.44 | 17.90 | 17.59 | 27.28 | 41.01 | 56.05 | 41.13 | 28.89 | 41.77 | 34.53 |
| General-purpose harnesses | |||||||||||
| System | Originality | Impact | Feasibility | Clarity | Specificity | Weighted mean |
| AI Scientist-v2 | 6.900 | 6.275 | 6.625 | 7.950 | 7.750 | 6.852 |
| Codex | 6.897 | 6.256 | 6.205 | 8.000 | 7.872 | 6.786 |
| Claude Code | 6.850 | 6.150 | 5.825 | 7.800 | 7.675 | 6.634 |
| Sage-Taiyi | 7.300 | 6.525 | 7.050 | 8.100 | 8.175 | 7.195 |
| Research area | Scientific contribution and outcome |
| Metal catalysis | Developed a cobalt-catalysed route to tetrasubstituted allenyl ketones, raising the model-reaction yield from trace amounts to 84% through reaction-condition optimization. |
| Photochemistry | Developed a photocatalytic route to site-selective allylic amination with heteroaryl amines, increasing the model-reaction yield from 13% to 69% . |
| Metamaterials | Designed a multilayer electromagnetic filter and relaxed a restrictive thickness constraint, achieving simulated average transmission of 6.2% in the stopband and 94.5% in the passband . |
| Alloy design | Jointly designed and optimized magnesium-alloy composition and heat treatment, producing an alloy with a mean measured tensile strength of 342 MPa . |
| Compressor engineering | Developed and refined a centrifugal-compressor design, achieving a CFD-evaluated impeller efficiency of 91.5% at a pressure ratio of 4.0 . |
| Quantity / variable | Search range | Unit / context | Best value |
| Optimization reward | – | Dimensionless | |
| Unit-cell period | mm | ||
| Jerusalem-cross arm length | mm | ||
| T-bar end-load length | mm | ||
| Jerusalem-cross linewidth | mm | ||
| Drude wire-grating pitch | mm |
| Quantity / variable | Search range | Unit / context | Best value |
| Optimization reward | – | Dimensionless | |
| Nominal yttrium content | wt.% | ||
| Nominal neodymium content | wt.% | ||
| Nominal gadolinium content | wt.% | ||
| Nominal zirconium content | wt.%; Mg balance | ||
| Solution-treatment temperature |
| Quantity / variable | Search range | Unit / context | Best value |
| Optimization reward | – | Efficiency fraction | |
| Outlet blade angle | ∘ | ||
| Inlet blade angle | ∘ | ||
| Main-blade count | Blades | ||
| Inlet shroud diameter | mm | ||
| CFD pressure ratio | – | Dimensionless |
Autonomous Scientific Discovery
Autonomous scientific discovery develops AI systems that generate, test, and refine scientific hypotheses using data, computation, and experiments.
See all 137 papers