The DOI matches its Crossref record; the references it cites are not checked yet.
Agentic AI framework for accelerated catalyst design in biomass valorization via small language models and automated machine learning
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A second group of studies used hybrid human-in-the-loop designs, where the agentic layer guided design or analysis but final judgment remained partly manual [20,22,27,30,31].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [30]
In the citing paper
“Catalysis and adsorption tasks formed the largest application block, represented by six studies on electrocatalyst design, adsorption-configuration search, biomass-valorization catalysis, MOF catalyst optimization, and single-atom-alloy discovery [19,20,27,28,30,34].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [30]
In the citing paper
“In several papers, the strongest reproducibility evidence came from public code, tutorials, datasets, or supplementary traces [18-21,23,25,28,30,31,35-42].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [30]
In the citing paper
“Others act more as discovery managers around retrieval, ranking, surrogate models, or protocol navigation [19,20,26,30,41].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [30]
In the citing paper
“Hybrid human-in-the-loop systems accounted for four of the six experimentally validated papers, which suggests that human oversight appears to be retained more often where the downstream consequences of an incorrect decision are more costly or irreversible, although the small sample precludes strong inference [20,22,27,30,31].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [30]
Citations
The citation lists haven’t been fetched yet
References 44 · Cited by 1
Research works printed but not linked: 17
- Abed, J. et al. Open catalyst experiments 2024 (OCx24): bridging experiments and computational models. Preprint at doi:10.48550/arXiv.2411.11783 (2024). · DOI
- Lai, N. S. et al. An artificial intelligence (AI) workflow for catalyst design and optimization. Preprint at doi:10.48550/arXiv.2402.04557 (2024). · DOI
- Xu, Y. et al. AI-empowered catalyst discovery: a survey from classical machine learning approaches to large language models. Preprint at doi:10.48550/arXiv.2502.13626 (2025). · DOI
- Zou, 2025, Prediction of biochar from thermochemical conversion of biomass—advances in artificial neural network application, J. Renew. Sustain. Energy, 17, 10.1063/5.0284714 · DOI
- Askell, A. et al. A general language assistant as a laboratory for alignment. Preprint at doi:10.48550/arXiv.2112.00861 (2021). · DOI · Paper page
- Cao, S. et al. Agents for self-driving laboratories applied to quantum computing. Preprint at doi:10.48550/arXiv.2412.07978 (2024). · DOI
- Xu, M. et al. Creative robot tool use with large language models. Preprint at doi:10.48550/arXiv.2310.13065 (2023). · DOI · Paper page
- Belcak, P. et al. Small language models are the future of agentic AI. Preprint at doi:10.48550/arXiv.2506.02153 (2025). · DOI · Paper page
- Abdin, M. et al. Phi-3 technical report: a highly capable language model locally on your phone. Preprint at doi:10.48550/arXiv.2404.14219 (2024). · DOI · Paper page
- Zhang, P., Zeng, G., Wang, T. & Lu, W. TinyLlama: an open-source small language model. Preprint at doi:10.48550/arXiv.2401.02385 (2024). · DOI
- Wolf, T. et al. Huggingface's transformers: state-of-the-art natural language processing. Preprint at doi:10.48550/arXiv.1910.03771 (2020). · DOI · Paper page
- Kumar, A. et al. OverThink: slowdown attacks on reasoning LLMs. Preprint at doi:10.48550/arXiv.2502.02542 (2025). · DOI · Paper page
- Müller, S., Feurer, M., Hollmann, N. & Hutter, F. PFNs4BO: In-Context Learning for Bayesian Optimization. in Proceedings of the 40th International Conference on Machine Learning 25444–25470 (PMLR, 2023).
- Feurer, 2022, Auto-sklearn 2.0: hands-free AutoML via meta-learning, J. Mach. Learn. Res., 23
- Pedregosa, 2011, Scikit-learn: machine learning in Python, J. Mach. Learn. Res., 12, 2825
- Hysmith, 2024, The future of self-driving laboratories: from human in the loop interactive AI to gamification, Dig. Dis., 3, 621
- Darvish, 2025, ORGANA: A robotic assistant for automated chemistry experimentation and characterization, Matter, 8, 10.1016/j.matt.2024.10.015 · DOI
Metadata
- Authors
- Liu, A., Kim, G., & Song, H.
- Affiliations
- University of Calgary (CA)
- Corresponding author
- Song, Hua
- ORCID
- Song, Hua
- Venue
- Chemical Engineering Journal
- Publisher
- Elsevier BV
- Published
- 2026-05
- Volume
- 535
- Pages
- 175701
- ISSN
- 1385-8947 (ISSN-L)
- OpenAlex
- W7143318597
- Cited by
- 1
- References
- 44
- Citations by year
- 2026: 1
- FWCI
- 1.37
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Chemical Engineering Journal (publishedVersion)
- Funders
- Natural Sciences and Engineering Research Council of Canada (ALLRP/591054-2023)
- Alberta Innovates (232404435)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemical Engineering › Catalysis › Catalysis for Biomass Conversion
- Physical Sciences › Energy › Fuel Technology › Thermochemical Biomass Conversion Processes
- Keywords
- agentic AI, small language models, automated machine learning, catalyst design, biomass valorization, deoxygenation, catalyst discovery, local deployment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Agentic AI framework for accelerated catalyst design in biomass valorization via small language models and automated machine learning. https://app.cochat.ai/papers/10.1016/j.cej.2026.175701
- The paper
- Liu, A., Kim, G., & Song, H. (2026). Agentic AI framework for accelerated catalyst design in biomass valorization via small language models and automated machine learning. Chemical Engineering Journal. https://doi.org/10.1016/j.cej.2026.175701
