Human-Machine Collaborative Design of SnTe-Based Thermoelectric Materials via a Multiagent Framework Leveraging Large Language Models
Abstract
Herein, we present an innovative large language model (LLM)-driven multiagent collaborative framework for the human-machine collaborative design of SnTe-based thermoelectric materials. Composed of strategy planning and reasoning modules, this framework efficiently extracts implicit domain knowledge from extensive literature and integrates historical experimental data to deduce optimization strategies and compositional ratio ranges, representing a novel paradigm that transcends traditional empirical and computational approaches in material design. Under the guidance of LLM, experimental results validate its efficacy: the incorporation of Sb, Ge, and Cu elements not only optimizes carrier concentration but also induces multiscale defects, synergistically modulating electrical and thermal transport properties. Notably, the (Sn 0.58 Sb 0.12 Ge 0.3 Te) 0.95 (Cu 2 Te) 0.05 sample achieves a zT value of ∼1.2, marking a 40% increase compared to Sb-doped SnTe and a 267% rise relative to SnTe prepared by the same method, directly demonstrating that LLM guidance can significantly enhance material performance. This research not only showcases the potential of LLMs to revolutionize thermoelectric material development but also provides a valuable reference for high-performance material design in broader energy-related fields with implications for improving waste heat recovery and solid-state cooling technologies.
Integrity signals
Registry
Cites
Statistics
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?
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.
“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 [22]
The remaining literature was distributed across general materials-workflow papers, atomistic simulation infrastructures, MOF and porous-material screening, and polymer simulation.
“The remaining literature was distributed across general materials-workflow papers, atomistic simulation infrastructures, MOF and porous-material screening, and polymer simulation [17,21,22,24-26,32,35-42].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [22]
In other papers, the workflow could be reconstructed only partially from supporting information, and prompt logs, failure traces, or decision histories remained incomplete.
“In others, the workflow could be reconstructed only partially from supporting information, and prompt logs, failure traces, or decision histories remained incomplete [17,22,24,26,27,29,33,34].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [22]
Other papers were more demonstrative, emphasizing workflow feasibility, design navigation, or case-based success rather than tightly standardized metrics.
“Other papers were more demonstrative, emphasizing workflow feasibility, design navigation, or case-based success rather than tightly standardized metrics [17,18,21,22,35,37-39,41].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [22]
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.
“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 [22]
Cites
From Louvain to Leiden: guaranteeing well-connected communities
Traag, V. A., Waltman, L., & van Eck, N. J. (2019) · Scientific Reports · doi:10.1038/s41598-019-41695-z · Cited by 5,635 · see citing works
Convergence of electronic bands for high performance bulk thermoelectrics
Pei, Y., Shi, X., LaLonde, A. D., Wang, H., Chen, L., & Snyder, G. J. (2011) · Nature · doi:10.1038/nature09996 · Cited by 4,281 · see citing works
Lower limit to the thermal conductivity of disordered crystals
Cahill, D. G., Watson, S. K., & Pohl, R. O. (1992) · Physical Review B · doi:10.1103/physrevb.46.6131 · Cited by 2,617 · see citing works
Compromise and Synergy in High‐Efficiency Thermoelectric Materials
Zhu, T., Liu, Y., Fu, C., Heremans, J. P., Snyder, G. J., & Zhao, X. (2017) · Advanced Materials · doi:10.1002/adma.201605884 · Cited by 1,621 · see citing works
Zhao, L., Wu, H., Hao, S., Wu, C., Zhou, X., Biswas, K., He, J., Hogan, T. P., Uher, C., Wolverton, C. M., et al. (2013) · Energy & Environmental Science · doi:10.1039/c3ee42187b · Cited by 768 · see citing works
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681 · see citing works
Tan, G., Shi, F., Hao, S., Chi, H., Zhao, L., Uher, C., Wolverton, C. M., Dravid, V. P., & Kanatzidis, M. G. (2015) · Journal of the American Chemical Society · doi:10.1021/jacs.5b00837 · Cited by 500 · see citing works
Li, W., Zheng, L., Ge, B., Lin, S., Zhang, X., Chen, Z., Chang, Y., & Pei, Y. (2017) · Advanced Materials · doi:10.1002/adma.201605887 · Cited by 434 · see citing works
Leveraging large language models for predictive chemistry
Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A., & Smit, B. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-023-00788-1 · Cited by 378 · see citing works
Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R., & Nanayakkara, S. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00530 · Cited by 337 · see citing works
Promising Thermoelectric Bulk Materials with 2D Structures
Zhou, Y., & Zhao, L. (2017) · Advanced Materials · doi:10.1002/adma.201702676 · Cited by 301 · see citing works
Banik, A., Vishal, B., Perumal, S., Datta, R., & Biswas, K. (2016) · Energy & Environmental Science · doi:10.1039/c6ee00728g · Cited by 297 · see citing works
Impact of word embedding models on text analytics in deep learning environment: a review
Asudani, D. S., Nagwani, N. K., & Singh, P. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10419-1 · Cited by 274 · see citing works
Zhao, L., He, J., Wu, C., Hogan, T. P., Zhou, X., Uher, C., Dravid, V. P., & Kanatzidis, M. G. (2012) · Journal of the American Chemical Society · doi:10.1021/ja301772w · Cited by 266 · see citing works
Banik, A., Ghosh, T., Arora, R., Dutta, M., Pandey, J., Acharya, S., Soni, A., Waghmare, U. V., & Biswas, K. (2019) · Energy & Environmental Science · doi:10.1039/c8ee03162b · Cited by 227 · see citing works
Tan, G., Hao, S., Hanus, R. C., Zhang, X., Anand, S., Bailey, T. P., Rettie, A. J. E., Su, X., Uher, C., Dravid, V. P., et al. (2018) · ACS Energy Letters · doi:10.1021/acsenergylett.8b00137 · Cited by 202 · see citing works
Rationalizing phonon dispersion for lattice thermal conductivity of solids
Chen, Z., Zhang, X., Lin, S., Chen, L., & Pei, Y. (2018) · National Science Review · doi:10.1093/nsr/nwy097 · Cited by 183 · see citing works
Guo, F., Cui, B., Liu, Y., Meng, X., Cao, J. H., Zhang, Y., He, R., Liu, W., Wu, H., Pennycook, S. J., et al. (2018) · Small · doi:10.1002/smll.201802615 · Cited by 175 · see citing works
Multiple effects of Bi doping in enhancing the thermoelectric properties of SnTe
Zhou, Z., Yang, J., Jiang, Q., Luo, Y., Zhang, D., Ren, Y., He, X., & Xin, J. (2016) · Journal of Materials Chemistry A · doi:10.1039/c6ta04240f · Cited by 170 · see citing works
Lee, Y., Lo, S., Androulakis, J., Wu, C., Zhao, L., Chung, D. Y., Hogan, T. P., Dravid, V. P., & Kanatzidis, M. G. (2013) · Journal of the American Chemical Society · doi:10.1021/ja400069s · Cited by 150 · see citing works
Interstitial Defects Improving Thermoelectric SnTe in Addition to Band Convergence
Zheng, L., Li, W., Lin, S., Li, J., Chen, Z., & Pei, Y. (2017) · ACS Energy Letters · doi:10.1021/acsenergylett.6b00671 · Cited by 148 · see citing works
Liu, J., Wang, P., Wang, M., Xu, R. C., Zhang, J., Liu, J., Li, D., Liang, N., Du, Y., Chen, G., et al. (2018) · Nano Energy · doi:10.1016/j.nanoen.2018.09.025 · Cited by 133 · see citing works
State of What Art? A Call for Multi-Prompt LLM Evaluation
Mizrahi, M., Kaplan, G., Malkin, D., Dror, R., Shahaf, D., & Stanovsky, G. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00681 · Cited by 113 · see citing works
Li, X., Liu, J., Li, S. L., Zhang, J., Li, D., Xu, R. C., Zhang, Q., Zhang, X., Xu, B., Zhang, Y., et al. (2019) · Nano Energy · doi:10.1016/j.nanoen.2019.104261 · Cited by 111 · see citing works
Self-citationDesigning band engineering for thermoelectrics starting from the periodic table of elements
Tan, X., Wang, H., Liu, G., Noudem, J., Hu, H., Xu, J., Shao, H., & Jiang, J. (2018) · Materials Today Physics · doi:10.1016/j.mtphys.2018.10.004 · Cited by 97 · see citing works
Gan, Y., Wang, G., Zhou, J., & Sun, Z. (2021) · npj Computational Materials · doi:10.1038/s41524-021-00645-y · Cited by 87 · see citing works
Constructing van der Waals gaps in cubic-structured SnTe-based thermoelectric materials
Xu, X. C., Cui, J., Yu, Y., Zhu, B., Huang, Y., Xie, L. H., Wu, D., & He, J. (2020) · Energy & Environmental Science · doi:10.1039/d0ee02638g · Cited by 85 · see citing works
Electronic structure modulation strategies in high-performance thermoelectrics
Dutta, M., Ghosh, T., & Biswas, K. (2020) · APL Materials · doi:10.1063/5.0002129 · Cited by 84 · see citing works
Bafekry, A., Faraji, M., Fadlallah, M. M., Hoat, D. M., Jappor, H. R., Sarsari, I. A., Ghergherehchi, M., & Feghhi, S. A. H. (2021) · Physical Chemistry Chemical Physics · doi:10.1039/d1cp03706d · Cited by 80 · see citing works
Bafekry, A., Obeid, M. M., Nguyen, C. V., Ghergherehchi, M., & Tagani, M. B. (2020) · Journal of Materials Chemistry A · doi:10.1039/d0ta02847a · Cited by 73 · see citing works
Bafekry, A., Shahrokhi, M., Shafique, A., Jappor, H. R., Fadlallah, M. M., Stampfl, C., Ghergherehchi, M., Mushtaq, M. A., Feghhi, S. A. H., & Gogova, D. S. (2021) · ACS Omega · doi:10.1021/acsomega.0c06024 · Cited by 69 · see citing works
High Thermoelectric Performance in SnTe Nanocomposites with All-Scale Hierarchical Structures
Jiang, Q., Hu, H., Yang, J., Xin, J., Li, S., Viola, G., & Yan, H. (2020) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.0c03349 · Cited by 68 · see citing works
Probing the limitations of multimodal language models for chemistry and materials research
Alampara, N., Schilling-Wilhelmi, M., Ríos-García, M., Mandal, I., Khetarpal, P., Grover, H. S., Krishnan, N. M. A., & Jablonka, K. M. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00836-3 · Cited by 54 · see citing works
Thermoelectric properties of In-Hg co-doping in SnTe: Energy band engineering
Tan, X., Liu, G., Xu, J., Tan, X., Shao, H., Hu, H., Jiang, H., Lu, Y., & Jiang, J. (2017) · Journal of Materiomics · doi:10.1016/j.jmat.2017.12.001 · Cited by 52 · see citing works
Hong, T., Wang, D., Qin, B., Zhang, X., Chen, Y., Gao, X., & Zhao, L. (2021) · Materials Today Physics · doi:10.1016/j.mtphys.2021.100505 · Cited by 47 · see citing works
Self-citationEnhanced Thermoelectric Performance of SnTe-Based Materials via Interface Engineering
Tian, B.-Z., Chen, J., Jiang, X.-P., Tang, J., Zhou, D., Sun, Q., Yang, L., & Chen, Z. (2021) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.1c16053 · Cited by 47 · see citing works
Liu, X., Zhang, B., Chen, Y., Wu, H., Wang, H., Yang, M., Wang, G., Xu, J., Zhou, X., & Han, G. (2020) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.0c13651 · Cited by 41 · see citing works
Self-citationA, W. F. V. G., & Oostenbrink, C. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00823 · Cited by 40 · see citing works
Lee, Y. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-13129-5 · Cited by 40 · see citing works
Synergistic boost of output power density and efficiency in In-Li–codoped SnTe
Guo, F., Wu, H., Zhu, J., Yao, H., Zhang, Y., Cui, B., Zhang, Q., Yu, B., Pennycook, S. J., Cai, W. H., et al. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1911085116 · Cited by 38 · see citing works
Self-citationAI‐Driven Defect Engineering for Advanced Thermoelectric Materials
Fu, C., Cheng, M., Hung, N. T., Rha, E., Chen, Z., Okabe, R., Carrizales, D. C., Mandal, M., Cheng, Y. Q., & Li, M. (2025) · Advanced Materials · doi:10.1002/adma.202505642 · Cited by 38 · see citing works
Enhancement of Thermoelectric Properties in SnTe with (Ag, In) Co-Doping
Li, J. Q., Yang, N., Li, S., Li, Y., Liu, F. S., & Ao, W. (2017) · Journal of Electronic Materials · doi:10.1007/s11664-017-5745-9 · Cited by 34 · see citing works
Nanostructuring SnTe to improve thermoelectric properties through Zn and Sb co-doping
Kihoi, S. K., & Lee, H. S. (2020) · Sustainable Energy & Fuels · doi:10.1039/d0se01081b · Cited by 33 · see citing works
Softmax function based intuitionistic fuzzy multi-criteria decision making and applications
Yu, D. (2015) · Operational Research · doi:10.1007/s12351-015-0196-7 · Cited by 28 · see citing works
High Thermoelectric Performance of SnTe via In Doping and Cu1.75Se Nanostructuring Approach
Li, D., Ming, H., Li, J., Zhang, J., Qin, X., & Xu, W. (2019) · ACS Applied Energy Materials · doi:10.1021/acsaem.9b02061 · Cited by 26 · see citing works
LLM Comparator: Interactive Analysis of Side-by-Side Evaluation of Large Language Models
Kahng, M., Tenney, I., Pushkarna, M., Liu, M. X., Wexler, J., Reif, E., Kallarackal, K., Chang, M., Terry, M. A., & Dixon, L. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3456354 · Cited by 26 · see citing works
Thermoelectric performance of SnTe alloys with In and Sb co-doped near critical solubility limit
Wang, T., Wang, H., Su, W., Zhai, J., Wang, X., Chen, T., & Wang, C. (2019) · Journal of Materials Science · doi:10.1007/s10853-019-03502-y · Cited by 24 · see citing works
Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
Zhang, Q., Chen, Q., Li, Y., Liu, J., & Wang, W. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688078 · Cited by 24 · see citing works
Self-citationApplications of deep language models for reflective writings
Nehyba, J., & Štefánik, M. (2022) · Education and Information Technologies · doi:10.1007/s10639-022-11254-7 · Cited by 23 · see citing works
Relation extraction: advancements through deep learning and entity-related features
Zhao, Y., Yuan, X., Yuan, Y., Deng, S., & Quan, J. (2023) · Social Network Analysis and Mining · doi:10.1007/s13278-023-01095-8 · Cited by 22 · see citing works
Su, H., Han, Y., Xie, L., Jiang, M., Wang, Z., Miao, Z., Liu, G., Zhou, M., Huang, R., & Li, L. (2023) · Journal of Materials Chemistry C · doi:10.1039/d3tc00077j · Cited by 16 · see citing works
Self-citationAn adaptive Physics-based feature engineering approach for Machine Learning-assisted alloy discovery
Soofi, Y. J., Gu, Y., & Liu, J. (2023) · Computational Materials Science · doi:10.1016/j.commatsci.2023.112248 · Cited by 16 · see citing works
Boosting thermoelectrics by alloying Cu2Se in SnTe-CdTe compounds
Chen, Z., Li, J., Tang, J., Zhang, F., Zhong, Y., Liu, H., & Ang, R. (2021) · Journal of Material Science and Technology · doi:10.1016/j.jmst.2021.02.012 · Cited by 15 · see citing works
MARIE: A Context-Aware Term Mapping with String Matching and Embedding Vectors
Kim, H. K., Choi, S. W., Bae, Y. S., Choi, J., Kwon, H., Lee, C. P., Lee, H., & Ko, T. (2020) · Applied Sciences · doi:10.3390/app10217831 · Cited by 9 · see citing works
Su, H., Miao, Z., Peng, Y. D., Zhao, Y., Wu, S., Jiang, M., Zhou, M., Huang, R., & Li, L. (2022) · Physical Chemistry Chemical Physics · doi:10.1039/d2cp04241j · Cited by 9 · see citing works
Self-citationDon’t Stop Believin’: A Unified Evaluation Approach for LLM Honeypots
Weber, S. B., Feger, M., & Pilgermann, M. (2024) · IEEE Access · doi:10.1109/access.2024.3472460 · Cited by 9 · see citing works
Political-RAG: using generative AI to extract political information from media content
Arslan, M., Munawar, S., & Cruz, C. (2024) · Journal of Information Technology & Politics · doi:10.1080/19331681.2024.2417263 · Cited by 9 · see citing works
Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document SegmentationPreprint
Zhang, Q., Chen, Q., Li, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.09278 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Alviz-Meza, A., Valencia-Arias, A., Rojas-Flores, S., & Diaz, F. (2026) · Data · doi:10.3390/data11070180
Yutomo, E. B., Faniandari, S., & Fahmi, M. R. F. (2026) · Next Materials · doi:10.1016/j.nxmate.2026.102164
LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems
Yang, S., Wang, Y., Tu, Q., Ran, N., & Lu, Y. (2026) · Journal of Materials Informatics · doi:10.20517/jmi.2026.38
Han, S., Lin, Y., Miao, N., Shu, Y., Li, Z., Zhu, L., Zhou, J., & Sun, Z. (2026) · Applied Energy · doi:10.1016/j.apenergy.2026.128925
- Authors
- Su, H., Lei, S., Chen, Y., Lv, Y., & Zhang, Q.
- Affiliations
- PLA Academy of Military Science (CN)
- Corresponding author
- Su, Haojian
- Zhang, Quan
- Venue
- ACS Applied Materials & Interfaces
- Publisher
- American Chemical Society (ACS)
- Published
- 2025-11-10
- Volume
- 17
- Issue
- 46
- Pages
- 63572-63584
- ISSN
- 1944-8244 (ISSN-L)
- 1944-8252
- OpenAlex
- W4416393373
- Cited by
- 4
- References
- 57
- Citations by year
- 2026: 4
- FWCI
- 0.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- ACS Applied Materials & Interfaces (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Key Research and Development Program of China (2024YFB3312904)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Advanced Thermoelectric Materials and Devices
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Materials Science › Materials Chemistry › Thermal properties of materials
- Keywords
- SnTe, thermoelectric materials, large language models, antimony doping, germanium doping, Cu2Te, carrier concentration, figure of merit ZT, waste heat recovery, solid-state cooling
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
