A traceable agentic framework for chemistry research query and analysis with ThermoML database
5 affiliations
- 1Center for Steel Electrification by Electrosynthesis
- 2Argonne National Laboratory
- 3Chemical Sciences and Engineering Division
- 4Physics Division
- 5Materials Science Division
Abstract
Reliable use of thermophysical databases in exploratory chemistry requires resolving heterogeneous identifiers, reconciling experimental conditions, and preserving numerical provenance across large, nested records. We present a hierarchical large language model (LLM) agent framework, implemented with a custom ReAct reasoning engine, that translates naturallanguage research questions into traceable retrieval and analysis workflows over the NIST ThermoML database. The framework combines hierarchical canonical identifiers, queryconditioned evidence compaction, deterministic inspection ledgers and numerical-grounding gates, and tool-assisted Redlich–Kister fitting. Five case studies are discussed in detail, representing chemistry tasks spanning data-rich and data-sparse retrieval, binary-mixture correlation, and open-ended cosolvent screening. For an ethanol–water equimolar density query, the system reduced ~190k characters of search output to 2k and precisely recovered a measured density of 859.3 kg m-3 at an ethanol mole fraction of 0.498, 298.15 K, and 100 kPa. For methanolethanol viscosity, it selected condition-aligned mixture and pure-component records, examined the fitting results at different orders, and produced a 2nd-order Redlich–Kister fit with 𝑅 = 0.982. Results for an open-ended iron-electrodeposition electrolyte design query synthesized evidence from approximately 12k measurements across 200 data blocks. However, with numerical grounding disabled for this specific case, the answer contained severe numerical hallucinations despite qualitatively coherent reasoning. These cases establish the feasibility of agent-assisted ThermoML research and identify identity management, evidence compaction, and deterministic numerical provenance as central design requirements for reliable chemistry-database research agents with some level of abstraction chemistry reasoning.
Related
- OptoMatKG: A Traceable Knowledge Graph Framework with Semantic Retrieval for Optoelectronic Materials Science
- Open Ontology of Polymer Chemistry: Accumulation and Self-Improving Memory Mechanisms for Polymer Research
- Essential Oil-Containing Mouthrinses for Plaque and Gingivitis Control: Formulation Chemistry, Human Salivary Biomarkers, Mechanistic Evidence, and Research Priorities
- How do the research evaluation requirements of Chinese universities, which are oriented towards paper publication, affect the development of chemistry graduate students and faculty members?
- El Agente Quntur: A research collaborator agent for quantum chemistry
BibTeX
@misc{sun2026traceable,
title = {{A traceable agentic framework for chemistry research query and analysis with ThermoML database}},
author = {Yunkai Sun and Adwaith Ravichandran and Hassan Harb and Rajeev S. Assary and Brian J. Ingram and Zhenzhen Yang},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15009028/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009028/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A traceable agentic framework for chemistry research query and analysis with ThermoML database
AU - Yunkai Sun
AU - Adwaith Ravichandran
AU - Hassan Harb
AU - Rajeev S. Assary
AU - Brian J. Ingram
AU - Zhenzhen Yang
PY - 2026
DA - 2026/09/17
PB - ChemRxiv
DO - 10.26434/chemrxiv.15009028/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009028/v1
AB - Reliable use of thermophysical databases in exploratory chemistry requires resolving heterogeneous identifiers, reconciling experimental conditions, and preserving numerical provenance across large, nested records. We present a hierarchical large language model (LLM) agent framework, implemented with a custom ReAct reasoning engine, that translates naturallanguage research questions into traceable retrieval and analysis workflows over the NIST ThermoML database. The framework combines hierarchical canonical identifiers, queryconditioned evidence compaction, deterministic inspection ledgers and numerical-grounding gates, and tool-assisted Redlich–Kister fitting. Five case studies are discussed in detail, representing chemistry tasks spanning data-rich and data-sparse retrieval, binary-mixture correlation, and open-ended cosolvent screening. For an ethanol–water equimolar density query, the system reduced ~190k characters of search output to 2k and precisely recovered a measured density of 859.3 kg m-3 at an ethanol mole fraction of 0.498, 298.15 K, and 100 kPa. For methanolethanol viscosity, it selected condition-aligned mixture and pure-component records, examined the fitting results at different orders, and produced a 2nd-order Redlich–Kister fit with 𝑅 = 0.982. Results for an open-ended iron-electrodeposition electrolyte design query synthesized evidence from approximately 12k measurements across 200 data blocks. However, with numerical grounding disabled for this specific case, the answer contained severe numerical hallucinations despite qualitatively coherent reasoning. These cases establish the feasibility of agent-assisted ThermoML research and identify identity management, evidence compaction, and deterministic numerical provenance as central design requirements for reliable chemistry-database research agents with some level of abstraction chemistry reasoning.
ER -