Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need Article Swipe

MAKE IMPACT

Bhishma Dedhia , Yuval Kansal , Niraj K. Jha · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.13966

Language models traditionally used for cross-domain generalization have recently demonstrated task-specific reasoning. However, their top-down training approach on general corpora is insufficient for acquiring abstractions needed for deep domain expertise. This may require a bottom-up approach that acquires expertise by learning to compose simple domain concepts into more complex ones. A knowledge graph (KG) provides this compositional structure, where domain primitives are represented as head-relation-tail edges and their paths encode higher-level concepts. We present a task generation pipeline that synthesizes tasks directly from KG primitives, enabling models to acquire and compose them for reasoning. We fine-tune language models on the resultant KG-grounded curriculum to demonstrate domain-specific superintelligence. While broadly applicable, we validate our approach in medicine, where reliable KGs exist. Using a medical KG, we curate 24,000 reasoning tasks paired with thinking traces derived from diverse medical primitives. We fine-tune the QwQ-32B model on this curriculum to obtain QwQ-Med-3 that takes a step towards medical superintelligence. We also introduce ICD-Bench, an evaluation suite to quantify reasoning abilities across 15 medical domains. Our experiments demonstrate that QwQ-Med-3 significantly outperforms state-of-the-art reasoning models on ICD-Bench categories. Further analysis reveals that QwQ-Med-3 utilizes acquired primitives to widen the performance gap on the hardest tasks of ICD-Bench. Finally, evaluation on medical question-answer benchmarks shows that QwQ-Med-3 transfers acquired expertise to enhance the base model's performance. While the industry's approach to artificial general intelligence (AGI) emphasizes broad expertise, we envision a future in which AGI emerges from the composable interaction of efficient domain-specific superintelligent agents.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2507.13966

PDF

https://arxiv.org/pdf/2507.13966

OA Status

green

OpenAlex ID

https://openalex.org/W4416167863

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416167863

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2507.13966

Digital Object Identifier

Title

Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-07-18

Full publication date if available

Authors

Bhishma Dedhia, Yuval Kansal, Niraj K. Jha

List of authors in order

Landing page

https://arxiv.org/abs/2507.13966

Publisher landing page

PDF URL

https://arxiv.org/pdf/2507.13966

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2507.13966

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload