Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 5 min ago
PreprintCC BYChemRxiv

Agentic Paper: From Tacit Expertise to AI-Ready Scientific Data and Knowledge Corpora

  • Luke Schneider1,2,3
  • Ganesh Narasimha2,3
  • Sumner B. Harris2,3
  • Ralph Bulanadi2,3
  • Asraful Haque2,3
  • Rama Vasudevan2,3
  • Jiawei Gong1,2,3
  • Yongtao Liu2,3
  1. 1Behrend College
  2. 2Center for Nanophase Materials Sciences
  3. 3Oak Ridge National Laboratory
Open at sourcePDFDOICite

Abstract

Artificial intelligence (AI) for domain science demands large, well-structured training corpora that integrate experimental data with not only explicit knowledge but also tacit expertise underlying scientific decisions. However, the tacit knowledge regarding practical reasoning, assumptions, failed attempts, parameter choices, and interpretive judgment is often held by authors and unpublished, hindering its use for AI development. Here, we propose Agentic Paper, a large language model (LLM)-enabled, author-curated scientific publishing framework that organizes these resources into a structured Agentic Paper package accessible through LLM-based interfaces, enabling the integration of connected, AI-ready data, explicit knowledge, and tacit expertise. Within Agentic Paper, the LLM serves as an interactive reasoning and orchestration layer that connects knowledge content with raw and processed data, figures, methodological details, metadata, code, and author-provided interpretation. Case studies in materials synthesis and characterization demonstrate how the LLM-enabled framework supports questioning, data visualization and inspection, numerical verification, and preparation of AI-ready datasets. By combining author-based organization of scientific data and knowledge, Agentic Paper provides a scalable pathway toward provenance-rich training corpora and more reliable AI-enabled scientific workflows.

Related

  1. Scientific Symbiosis: Bridging Expertise and Fostering Effective Collaborations with Mass Spectrometrists
    Kara M. Joseph, Erin S. Baker
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  2. vibe-qc: expert-directed agentic engineering for scientific software development
    Michael F. Peintinger
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  3. Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments
    Takuya Isogawa, Ryotaro Okabe, Nutdech Phadetsuwannukun +2
    arXiv (Cornell University)PreprintLicence not statedFull text9 citedMaterials & polymersOpenAlex
  4. PolyReader: an agentic LLM pipeline for extracting structured data from unstructured polymer scientific literature
    Yuwei Shi, Xinyan Zhong, Yuqi Wei +3
    ChemRxivPreprintCC BYFull textMaterials & polymersChemRxiv
  5. MoSeS Enables Autonomous Chromatography Operation through Programmable Analytical Expertise
    Mohammad Haddadnia, Malcolm Sim, Han Hao +7
    ChemRxivPreprintCC BYFull textPhysical chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{schneider2026agentic,
  title = {{Agentic Paper: From Tacit Expertise to AI-Ready Scientific Data and Knowledge Corpora}},
  author = {Luke Schneider and Ganesh Narasimha and Sumner B. Harris and Ralph Bulanadi and Asraful Haque and Rama Vasudevan and Jiawei Gong and Yongtao Liu},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15007332/v2},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15007332/v2},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Agentic Paper: From Tacit Expertise to AI-Ready Scientific Data and Knowledge Corpora
AU  - Luke Schneider
AU  - Ganesh Narasimha
AU  - Sumner B. Harris
AU  - Ralph Bulanadi
AU  - Asraful Haque
AU  - Rama Vasudevan
AU  - Jiawei Gong
AU  - Yongtao Liu
PY  - 2026
DA  - 2026/10/02
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15007332/v2
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15007332/v2
AB  - Artificial intelligence (AI) for domain science demands large, well-structured training corpora that integrate experimental data with not only explicit knowledge but also tacit expertise underlying scientific decisions. However, the tacit knowledge regarding practical reasoning, assumptions, failed attempts, parameter choices, and interpretive judgment is often held by authors and unpublished, hindering its use for AI development. Here, we propose Agentic Paper, a large language model (LLM)-enabled, author-curated scientific publishing framework that organizes these resources into a structured Agentic Paper package accessible through LLM-based interfaces, enabling the integration of connected, AI-ready data, explicit knowledge, and tacit expertise. Within Agentic Paper, the LLM serves as an interactive reasoning and orchestration layer that connects knowledge content with raw and processed data, figures, methodological details, metadata, code, and author-provided interpretation. Case studies in materials synthesis and characterization demonstrate how the LLM-enabled framework supports questioning, data visualization and inspection, numerical verification, and preparation of AI-ready datasets. By combining author-based organization of scientific data and knowledge, Agentic Paper provides a scalable pathway toward provenance-rich training corpora and more reliable AI-enabled scientific workflows.
ER  -