CoChat

Adsorb-Agent: autonomous identification of stable adsorption configurations via a large language model agent

Open access
Ock, Janghoon, Meda, Radheesh Sharma, Vinchurkar, Tirtha, Jadhav, Yayati, Barati Farimani, Amir · 2026 · Digital Discovery

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Abstract

Adsorb-Agent: an LLM-powered agent for determining the most stable adsorption configurations using reasoning and prior knowledge.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1039/d5dd00298b

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Adsorb-Agent framework. (a) Overall process for identifying the most stable con fi guration by combining the LLM modules and tools. The left yellow box represents the part where the LLM modules are involved, comprising three components -Solution Planner, Critic, and Binding Indexer. These modules are powered by LLM APIs such as GPT-4o, GPT-4o-mini, Claude-3.7-Sonnet, and DeepSeek-Chat. (b) Illustration of the iterative interaction between the Solution Planner and Critic modules. (c) Example solution for the NNH -CuPd3 (1, 1, 1) system. The system metadata comprise the following in order: the SMILES representation of the adsorbate molecule, the chemical composition of the bulk catalyst, the Miller index, the Materials Project ID, the shift, and the top. (d) Example of binding index derivation from the Binding Indexer module.
Fig. 1 Adsorb-Agent framework. (a) Overall process for identifying the most stable con fi guration by combining the LLM modules and tools. The left yellow box represents the part where the LLM modules are involved, comprising three components -Solution Planner, Critic, and Binding Indexer. These modules are powered by LLM APIs such as GPT-4o, GPT-4o-mini, Claude-3.7-Sonnet, and DeepSeek-Chat. (b) Illustration of the iterative interaction between the Solution Planner and Critic modules. (c) Example solution for the NNH -CuPd3 (1, 1, 1) system. The system metadata comprise the following in order: the SMILES representation of the adsorbate molecule, the chemical composition of the bulk catalyst, the Miller index, the Materials Project ID, the shift, and the top. (d) Example of binding index derivation from the Binding Indexer module.CC-BY-NC · From the PDF
Fig. 2 Comparison of search space between the algorithmic approach and Adsorb-Agent. Left panels show solutions derived by Adsorb-Agent, while right panels present atomic visualizations of surfaces with initial adsorption sites for (a) NNH -CuPd3 (111), (b) OH -Pt (111), and (c) OCHCH3 -HfZn3 (110) (blue dots: initial sites; red stars: relaxed stable sites).
Fig. 2 Comparison of search space between the algorithmic approach and Adsorb-Agent. Left panels show solutions derived by Adsorb-Agent, while right panels present atomic visualizations of surfaces with initial adsorption sites for (a) NNH -CuPd3 (111), (b) OH -Pt (111), and (c) OCHCH3 -HfZn3 (110) (blue dots: initial sites; red stars: relaxed stable sites).CC-BY-NC · From the PDF
Fig. 3 Quantitative analysis of Adsorb-Agent results. (a) Success Rate (SR) and Lower Energy Discovery Rate (LEDR) across di ff erent categories; (b) Reduced Search Space Rate (RSR) obtained from three independent runs. For each system, the number of con fi gurations is averaged over the three runs, and the error bars indicate the standard deviation; (c) consistency rate across independent runs.
Fig. 3 Quantitative analysis of Adsorb-Agent results. (a) Success Rate (SR) and Lower Energy Discovery Rate (LEDR) across di ff erent categories; (b) Reduced Search Space Rate (RSR) obtained from three independent runs. For each system, the number of con fi gurations is averaged over the three runs, and the error bars indicate the standard deviation; (c) consistency rate across independent runs.CC-BY-NC · From the PDF
Fig. 4 Comparison of relaxed adsorption con fi gurations (upper panels) and energy distributions (lower panels). (a) NNH -CuPd3 (111); (b) OH -Pt (111); (c) OCHCH3 -Hf2Zn5 (110). The energy distributions are generated by combining results from all three independent runs.
Fig. 4 Comparison of relaxed adsorption con fi gurations (upper panels) and energy distributions (lower panels). (a) NNH -CuPd3 (111); (b) OH -Pt (111); (c) OCHCH3 -Hf2Zn5 (110). The energy distributions are generated by combining results from all three independent runs.CC-BY-NC · From the PDF
Fig. 5 Comparison of Adsorb-Agent performance using di ff erent language models. (a) Success Rate (SR) and Lower Energy Discovery Rate (LEDR) across models; (b) box plots of Reduced Search Space Rate (RSR) for each language model over three iterations, where the red line indicates the median, the box represents the interquartile range (IQR), and the whiskers extend to the minimum and maximum values within 1.5 times the IQR; (c) consistency ratios for total (surface and adsorbate categories) across independent runs.
Fig. 5 Comparison of Adsorb-Agent performance using di ff erent language models. (a) Success Rate (SR) and Lower Energy Discovery Rate (LEDR) across models; (b) box plots of Reduced Search Space Rate (RSR) for each language model over three iterations, where the red line indicates the median, the box represents the interquartile range (IQR), and the whiskers extend to the minimum and maximum values within 1.5 times the IQR; (c) consistency ratios for total (surface and adsorbate categories) across independent runs.CC-BY-NC · From the PDF
Image 6
CC-BY-NC · From the PDF
Image 7
CC-BY-NC · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

2 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 36 references

Research works printed but not linked: 7

  1. J. A.Dumesic , G. W.Huber and M.Boudart , Handbook of Heterogeneous Catalysis , John Wiley & Sons, Ltd , 2008
  2. Jadhav, 2025, Addit. Manuf., 114, 105027
  3. Ock, 2024, Nat. Mach. Intell., 1
  4. A.Radford and K.Narasimhan , Improving Language Understanding by Generative Pre-Training , 2018 , https://api.semanticscholar.org/CorpusID:49313245
  5. OpenAI GPT-4 Technical Report , 2023 , https://cdn.openai.com/papers/gpt-4.pdf
  6. A.Vaswani , N.Shazeer , N.Parmar , J.Uszkoreit , L.Jones , A. N.Gomez , Ł.Kaiser and I.Polosukhin , Attention is all you need , Advances in Neural Information Processing Systems , 2017 , vol. 30
  7. H.Lu , W.Liu , B.Zhang , B.Wang , K.Dong , B.Liu , J.Sun , T.Ren , Z.Li , Y.Sun , C.Deng , H.Xu , Z.Xie and C.Ruan , DeepSeek-VL: Towards Real-World Vision-Language Understanding , 2024

Cited by

Metadata

Authors
Ock, J., Meda, R. S., Vinchurkar, T., Jadhav, Y., & Barati Farimani, A.
Affiliations
  • University of Nebraska–Lincoln (US)
  • Carnegie Mellon University (US)
  • Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213, USA
Venue
Digital Discovery
Published
2026
Volume
5
Issue
2
Pages
617-629
ISSN
2635-098X (ISSN-L)
OpenAlex
W7116039842
Cited by
3
References
35
Citations by year
2026: 3
FWCI
0.63
Type
journal article
Language
en
Open access
Locations
Digital Discovery (publishedVersion, cc-by-nc)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
  • Physical Sciences › Chemistry › Physical and Theoretical Chemistry › Surface Chemistry and Catalysis
Keywords
adsorption configuration, LLM agents, autonomous reasoning, adsorption stability, chemisorption

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.