pith. sign in

arxiv: 2606.01145 · v2 · pith:6UR3WSNDnew · submitted 2026-05-31 · 💻 cs.AI

Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches

Teddy Ferdinan , Bart{\l}omiej Koptyra , Miko{\l}aj Langner , Tomasz Adamczyk , {\L}ukasz Radli\'nski , Maciej Markiewicz , Aleksander Szcz\k{e}sny , Stanis{\l}aw Wo\'zniak
show 37 more authors
Tymoteusz Romanowicz Dzmitry Pihulski Mateusz Zbrocki Mateusz \'Smigielski Micha{\l} Rajkowski Mateusz Biedka Konrad Kie{\l}czy\'nski Konrad Wojtasik Jacek Duszenko Jan Eliasz Piotr Matys Micha{\l} Bernacki-Janson Maria Bellaniar Ismiati Latius Hermawan Wiktoria Mieleszczenko-Kowszewicz Anna Kubicka-Sowinska Grzegorz Chodak Karol Postawa Pawe{\l} Zyblewski Tomasz Szanda{\l}a {\L}ukasz Sterczewski Adrian Chajec Pawel Niewiadomski Piotr Gruber Marcin Wdowikowski S{\l}awomir Czarnecki Bart{\l}omiej Kryszak Dominik Drabik Tomasz Kajdanowicz Kamil Mamak Pawe{\l} Pre\'s Katarzyna Paczkowska Joachim Sobczuk Tomasz Zi\k{e}ba Jan Koco\'n Maciej Piasecki Przemys{\l}aw Kazienko
This is my paper

Pith reviewed 2026-06-28 17:33 UTC · model grok-4.3

classification 💻 cs.AI
keywords reasoning language modelsscientific disciplinesadoption surveymaturity assessmentERC classificationcross-disciplinary analysispublic resources
0
0 comments X

The pith

Reasoning language models show concentrated adoption in hard sciences with widening maturity gaps across 28 disciplines.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey maps the use of reasoning language models across all major branches of science using the European Research Council discipline list. It finds that development and application remain heavily skewed toward physical sciences and engineering while social sciences, humanities, and parts of life sciences show far less activity. The authors rate each field by the presence of domain-specific training data, benchmarks, and applications, then show that restricting the view to publicly available items makes the differences larger. The work also catalogs popular implementation patterns, open challenges such as data scarcity and evaluation standards, and possible routes to wider use. A sympathetic reader would care because unequal access to these tools could translate directly into unequal research output between fields.

Core claim

RLM adoption is concentrated in hard science fields with substantial disparities in maturity across the 28 ERC disciplines; these disparities become even more pronounced when only publicly available resources are considered.

What carries the argument

A maturity-oriented assessment framework that scores each discipline according to the quantity and accessibility of domain-specific development and evaluation resources for reasoning language models.

If this is right

  • Disciplines rated low in maturity will continue to experience slower productivity gains from reasoning language models unless targeted resources appear.
  • Implementation patterns that succeed in high-maturity fields can be tested for transfer to lower-maturity fields.
  • Public-only resource gaps imply that open data and benchmark releases would be high-leverage actions for closing divides.
  • Future work should focus on the specific challenges of data scarcity and evaluation standards identified for lagging disciplines.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the maturity gaps persist, overall scientific progress could become more uneven as hard-science fields pull further ahead.
  • Prioritizing public datasets and shared benchmarks for under-served disciplines offers a direct lever to reduce the observed divides.
  • The same maturity lens could be reapplied in two or three years to test whether policy or community efforts have narrowed the differences.

Load-bearing premise

The 28 ERC discipline categories together with the authors' resource-based maturity ratings give a faithful picture of real differences in how ready each scientific branch is for reasoning language models.

What would settle it

A direct count of reasoning-language-model usage or resource creation per ERC discipline that finds roughly equal activity across hard sciences, life sciences, and social sciences and humanities would undermine the reported concentration and disparity.

Figures

Figures reproduced from arXiv: 2606.01145 by Adrian Chajec, Aleksander Szcz\k{e}sny, Anna Kubicka-Sowinska, Bart{\l}omiej Koptyra, Bart{\l}omiej Kryszak, Dominik Drabik, Dzmitry Pihulski, Grzegorz Chodak, Jacek Duszenko, Jan Eliasz, Jan Koco\'n, Joachim Sobczuk, Kamil Mamak, Karol Postawa, Katarzyna Paczkowska, Konrad Kie{\l}czy\'nski, Konrad Wojtasik, Latius Hermawan, {\L}ukasz Radli\'nski, {\L}ukasz Sterczewski, Maciej Markiewicz, Maciej Piasecki, Marcin Wdowikowski, Maria Bellaniar Ismiati, Mateusz Biedka, Mateusz \'Smigielski, Mateusz Zbrocki, Micha{\l} Bernacki-Janson, Micha{\l} Rajkowski, Miko{\l}aj Langner, Pawel Niewiadomski, Pawe{\l} Pre\'s, Pawe{\l} Zyblewski, Piotr Gruber, Piotr Matys, Przemys{\l}aw Kazienko, S{\l}awomir Czarnecki, Stanis{\l}aw Wo\'zniak, Teddy Ferdinan, Tomasz Adamczyk, Tomasz Kajdanowicz, Tomasz Szanda{\l}a, Tomasz Zi\k{e}ba, Tymoteusz Romanowicz, Wiktoria Mieleszczenko-Kowszewicz.

Figure 1
Figure 1. Figure 1: RLM maturity levels across 28 scientific disciplines based on all identified resources. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Maturity of Development Resources (MD) and Maturity of Evaluation Resources (ME) of three main research domains: Social [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Maturity of Development Resources (MD) and Maturity of Evaluation Resources (ME) for 28 scientific disciplines as calculated [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Current trends of RLM usage in science: (a) Specialized models over general, all-purpose models; (b) Explainability via reasoning [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Current challenges of RLM adoption in science: (a) Hallucination & unfaithful reasoning; (b) Limited interpolative analysis; (c) [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Future directions for RLM adoption in science: (a) Grounding on multimodal scientific data; (b) Management of scientific [PITH_FULL_IMAGE:figures/full_fig_p015_6.png] view at source ↗
read the original abstract

While Reasoning Language Models (RLMs) are rapidly emerging as powerful tools for scientific research, their impact is primarily concentrated in "hard science" fields. The slow -- or lack of -- adoption of RLMs in other branches of science is causing a widening gap in research productivity. In this survey, we provide the first comprehensive analysis of RLM adoption across 28 scientific disciplines following the classification used by the European Research Council (ERC), spanning the Social Sciences and Humanities, Physical Sciences and Engineering, and Life Sciences. We examine how RLMs are developed, evaluated, and applied across disciplines. Furthermore, we introduce a maturity-oriented assessment framework based on available domain-specific development and evaluation resources, revealing substantial disparities in RLM maturity that become even more pronounced when only publicly available resources are considered. Finally, we highlight current implementation paradigms that are gaining popularity across disciplines, current challenges, and future directions in enabling RLM adoption across science.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper surveys Reasoning Language Model (RLM) adoption across the 28 ERC disciplines spanning Social Sciences and Humanities, Physical Sciences and Engineering, and Life Sciences. It claims RLM use is concentrated in hard sciences, introduces a maturity-oriented assessment framework based on domain-specific development and evaluation resources, and reports substantial maturity disparities that widen when restricted to public resources. The work also reviews implementation paradigms, challenges, and future directions for broader adoption.

Significance. If the survey methodology and maturity framework can be made reproducible, the quantification of adoption gaps across all ERC branches would provide a useful reference for prioritizing RLM resource development in underrepresented fields and could help close the described productivity gap.

major comments (3)
  1. [Abstract] Abstract and the section defining the maturity-oriented assessment framework: no explicit search methodology, inclusion/exclusion criteria, or quantitative rules for resource counting and maturity-level thresholding are provided, so the central claim of discipline-level disparities rests on an unvalidated classification procedure whose reproducibility is not demonstrated.
  2. [Maturity framework section] The section presenting the maturity framework and associated tables/figures: without inter-rater reliability checks or a reproducible scoring rubric, the reported widening of disparities under the public-resources restriction cannot be distinguished from classification artifacts.
  3. [Literature review section] The literature-selection description (likely §2 or §3): absence of a documented protocol for identifying domain-specific RLM papers and resources undermines the claim that the analysis is the 'first comprehensive' survey across all 28 ERC disciplines.
minor comments (2)
  1. Clarify notation for maturity levels and ensure every table or figure is explicitly referenced in the surrounding text.
  2. Add a limitations subsection that explicitly discusses potential biases in ERC classification and resource availability.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments highlighting the need for greater methodological transparency. We agree that reproducibility is essential for a survey of this scope and will revise the manuscript to include explicit documentation of the survey process, thereby strengthening the central claims regarding RLM adoption disparities.

read point-by-point responses

  1. Referee: [Abstract] Abstract and the section defining the maturity-oriented assessment framework: no explicit search methodology, inclusion/exclusion criteria, or quantitative rules for resource counting and maturity-level thresholding are provided, so the central claim of discipline-level disparities rests on an unvalidated classification procedure whose reproducibility is not demonstrated.

    Authors: We agree that the manuscript would benefit from an explicit methods description. In the revision we will insert a new 'Survey Methodology' subsection that details the literature search strategy across databases, the keywords and time bounds employed, inclusion/exclusion criteria for papers and resources, and the quantitative thresholds used to assign maturity levels. This addition will make the classification procedure reproducible and directly support the reported discipline-level disparities. revision: yes

  2. Referee: [Maturity framework section] The section presenting the maturity framework and associated tables/figures: without inter-rater reliability checks or a reproducible scoring rubric, the reported widening of disparities under the public-resources restriction cannot be distinguished from classification artifacts.

    Authors: We acknowledge the value of a documented rubric and consistency checks. The revised maturity-framework section will present the full scoring rubric used to evaluate domain-specific development and evaluation resources, together with the procedure followed for assigning levels. Where formal inter-rater reliability statistics were not computed, we will state this limitation and describe the steps taken to maintain classification consistency; any feasible post-hoc checks will be added. revision: yes

  3. Referee: [Literature review section] The literature-selection description (likely §2 or §3): absence of a documented protocol for identifying domain-specific RLM papers and resources undermines the claim that the analysis is the 'first comprehensive' survey across all 28 ERC disciplines.

    Authors: We will expand the literature-review section with a dedicated protocol subsection that records how domain-specific RLM papers and resources were identified for each of the 28 ERC disciplines. This documentation will clarify the breadth of coverage underlying the 'first comprehensive' characterization while remaining transparent about any practical constraints of the broad disciplinary scope. revision: yes

Circularity Check

0 steps flagged

Descriptive survey with no derivation chain, equations, or fitted predictions

full rationale

The paper is a survey providing analysis of RLM adoption across 28 ERC disciplines and introducing a maturity-oriented assessment framework based on domain-specific resources. It contains no equations, derivations, model parameters, or predictions that could reduce to inputs by construction. The framework is presented as an original contribution for classifying maturity levels from resource availability, with disparities reported as direct observations rather than any self-referential or fitted result. No self-citation chains, uniqueness theorems, or ansatzes are invoked in a load-bearing way. This is a standard descriptive survey whose central claims rest on external resource enumeration and ERC classification, making it self-contained with no circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The survey rests on the assumption that the ERC taxonomy is exhaustive and that maturity can be meaningfully scored from available development and evaluation resources. No free parameters or mathematical derivations are present. The maturity framework itself is an invented construct without independent validation in the abstract.

axioms (1)
  • domain assumption The European Research Council classification accurately partitions all scientific disciplines into 28 categories suitable for uniform comparison.
    Invoked to structure the analysis across Social Sciences and Humanities, Physical Sciences and Engineering, and Life Sciences.
invented entities (1)
  • maturity-oriented assessment framework no independent evidence
    purpose: To quantify RLM adoption maturity per discipline based on domain-specific resources.
    Newly introduced construct whose scoring rules and validation are not detailed in the abstract.

pith-pipeline@v0.9.1-grok · 5985 in / 1246 out tokens · 20457 ms · 2026-06-28T17:33:02.866257+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 119 canonical work pages · 1 internal anchor

  1. [1]

    Moore, Daniel M

    Suhaib Abdurahman, Alireza Salkhordeh Ziabari, Alexander K. Moore, Daniel M. Bartels, and Morteza Dehghani. 2025. A Primer for Evaluating Large Language Models in Social-Science Research.Advances in Methods and Practices in Psychological Science8, 2 (2025), 25152459251325174. arXiv:https://doi.org/10.1177/25152459251325174 doi:10.1177/25152459251325174

    work page doi:10.1177/25152459251325174 2025

  2. [2]

    Muntasir Adnan and Carlos C. N. Kuhn. 2025. Measuring and mitigating debugging effectiveness decay in code language models.Scientific Reports 15, 1 (18 Dec 2025), 44120. doi:10.1038/s41598-025-27846-5

    work page doi:10.1038/s41598-025-27846-5 2025

  3. [3]

    Said Al Faraby, Ade Romadhony, and Adiwijaya. 2024. Analysis of LLMs for educational question classification and generation.Computers and Education: Artificial Intelligence7 (2024), 100298. doi:10.1016/j.caeai.2024.100298

    work page doi:10.1016/j.caeai.2024.100298 2024

  4. [4]

    Nourah Alangari and Nouf AlShenaifi. 2025. N&N at QIAS 2025: Chain-of-Thought Ensembles with Retrieval-Augmented framework for Classical Arabic Islamic. InProceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, Kareem Darwish, Ahmed Ali, Ibrahim Abu Farha, Samia Touileb, Imed Zitouni, Ahmed Abdelali, Sharefah Al-Ghamdi, Sakha...

    work page doi:10.18653/v1/2025.arabicnlp-sharedtasks.121 2025

  5. [5]

    Asma Musabah Alkalbani, Ahmed Salim Alrawahi, Ahmad Salah, Venus Haghighi, Yang Zhang, Salam Alkindi, and Quan Z. Sheng. 2025. A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions.Information16, 6 (2025). doi:10.3390/info16060489

    work page doi:10.3390/info16060489 2025

  6. [6]

    Santiago Alonso Sousa, Syed Saad Ul Hassan Bukhari, Paulo Vinicius Steagall, Paweł M Bęczkowski, Antonio Giuliano, and Kate J Flay. 2025. Performance of large language models on veterinary undergraduate multiple-choice examinations: a comparative evaluation.Front Vet Sci12 (Aug. 2025), 1616566

    2025

  7. [7]

    Maryam Amirizaniani, Elias Martin, Maryna Sivachenko, Afra Mashhadi, and Chirag Shah. 2024. Can LLMs Reason Like Humans? Assessing Theory of Mind Reasoning in LLMs for Open-Ended Questions. InProceedings of the 33rd ACM International Conference on Information and Knowledge Management(Boise, ID, USA)(CIKM ’24). Association for Computing Machinery, New York...

    work page doi:10.1145/3627673.3679832 2024

  8. [8]

    Richardson, Austin C

    Jacy Reese Anthis, Ryan Liu, Sean M. Richardson, Austin C. Kozlowski, Bernard Koch, James Evans, Erik Brynjolfsson, and Michael Bernstein

  9. [9]

    arXiv:2504.02234 [cs.HC] https://arxiv.org/abs/2504.02234

    LLM Social Simulations Are a Promising Research Method. arXiv:2504.02234 [cs.HC] https://arxiv.org/abs/2504.02234

    arXiv

  10. [10]

    2026.System Card: Claude Opus 4.6

    Anthropic. 2026.System Card: Claude Opus 4.6. Technical Report. Anthropic. https://www-cdn.anthropic.com/ 14e4fb01875d2a69f646fa5e574dea2b1c0ff7b5.pdf Accessed: 2026-04-14

    2026

  11. [11]

    Antunes, Keith T

    Luis M. Antunes, Keith T. Butler, and Ricardo Grau-Crespo. 2024. Crystal structure generation with autoregressive large language modeling. Nature Communications15, 1 (06 Dec 2024), 10570. doi:10.1038/s41467-024-54639-7

    work page doi:10.1038/s41467-024-54639-7 2024

  12. [12]

    Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. InThe Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=hSyW5go0v8

    2024

  13. [13]

    Muhammad Ayoub, Hai Zhao, Lifeng Li, Dongjie Yang, Shabir Hussain, and Junaid Abdul Wahid. 2026. Structured clinical approach to enable large language models to be used for improved clinical diagnosis and explainable reasoning.Communications Medicine6, 1 (Jan. 2026), 86. doi:10.1038/s43856-025-01348-x

    work page doi:10.1038/s43856-025-01348-x 2026

  14. [14]

    Chaithanya Bandi, Ben Hertzberg, Geobio Boo, Tejas Polakam, Jeff Da, Sami Hassaan, Manasi Sharma, Andrew Park, Ernesto Hernandez, Dan Rambado, Ivan Salazar, Rafael Cruz, Chetan Rane, Ben Levin, Brad Kenstler, and Bing Liu. 2026. MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers. arXiv:2602.00933 [cs.SE] https://arxiv.org/abs...

    Pith/arXiv arXiv 2026

  15. [15]

    Barman, Sascha Caron, Emily Sullivan, Henk W

    Kristian G. Barman, Sascha Caron, Emily Sullivan, Henk W. de Regt, Roberto Ruiz de Austri, Mieke Boon, Michael Färber, Stefan Fröse, Tobias Golling, Luis G. Lopez, Faegheh Hasibi, Lukas Heinrich, Andreas Ipp, Rukshak Kapoor, Gregor Kasieczka, Daniel Kostić, Michael Krämer, Jesus Marco, Sydney Otten, Pawel Pawlowski, Pietro Vischia, Erik Weber, and Christo...

    work page doi:10.1140/epjc/s10052-025-14707-8 2025

  16. [16]

    Armin Berger, Sarthak Khanna, David Berghaus, and Rafet Sifa. 2025. Reasoning LLMs in the Medical Domain: A Literature Survey.arXiv preprint arXiv:2508.19097(2025)

    arXiv 2025

  17. [17]

    Montine, and Nima Aghaeepour

    Eloise Berson, Philip Chung, Camilo Espinosa, Thomas J. Montine, and Nima Aghaeepour. 2024. Unlocking human immune system complexity through AI.Nature Methods21 (2024), 1400–1402. doi:10.1038/s41592-024-02351-1

    work page doi:10.1038/s41592-024-02351-1 2024

  18. [18]

    Randolph, Matthew Muhoberac, Palak Manchanda, Katherine A

    Connor Beveridge, Sanjay Iyer, Caitlin E. Randolph, Matthew Muhoberac, Palak Manchanda, Katherine A. Walker, Shane Tichy, and Gaurav Chopra. 2025. CLAW-MRM: Comprehensive Lipidomics Automation Workflow for Multiple Reaction Monitoring Using Large Language Models. Analytical Chemistry97, 36 (2025), 19409–19418. arXiv:https://doi.org/10.1021/acs.analchem.4c...

    work page doi:10.1021/acs.analchem.4c05039 2025

  19. [19]

    Nathan Bigaud, Vincent Cabeli, Meltem Gürel, Arthur Pignet, John Klein, Gilles Wainrib, and Eric Durand. 2025. OwkinZero: Accelerating Biological Discovery with AI. arXiv:2508.16315 [cs.LG] https://arxiv.org/abs/2508.16315

    arXiv 2025

  20. [20]

    Bran, Sam Cox, Oliver Schilter, et al

    Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D. White, and Philippe Schwaller. 2024. Augmenting large language models with chemistry tools.Nature Machine Intelligence(2024). doi:10.1038/s42256-024-00832-8

    work page doi:10.1038/s42256-024-00832-8 2024

  21. [21]

    Fan Bu et al. 2025. An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage.arXiv preprint arXiv:2501.02039(2025). https://arxiv.org/abs/2501.02039

    arXiv 2025

  22. [22]

    Spears, Derya Unutmaz, Kevin Weil, Steven Yin, and Nikita Zhivotovskiy

    Sébastien Bubeck, Christian Coester, Ronen Eldan, Timothy Gowers, Yin Tat Lee, Alexandru Lupsasca, Mehtaab Sawhney, Robert Scherrer, Mark Sellke, Brian K. Spears, Derya Unutmaz, Kevin Weil, Steven Yin, and Nikita Zhivotovskiy. 2025. Early science acceleration experiments with GPT-5. arXiv:2511.16072 [cs.CL] https://arxiv.org/abs/2511.16072

    arXiv 2025

  23. [23]

    Quintina Campbell, Sam Cox, Jorge Medina, Brittany Watterson, and Andrew D White. 2025. MDCrow: Automating Molecular Dynamics Workflows with Large Language Models.arXiv preprint arXiv:2502.09565(2025)

    arXiv 2025

  24. [24]

    Jeffrey A. Cardille, Renee Johnston, Simon Ilyushchenko, Johan Kartiwa, Zahra Shamsi, Matthew Abraham, Khashayar Azad, Kainath Ahmed, Emma Bergeron Quick, Nuala Caughie, Noah Jencz, Karen Dyson, Andrea Puzzi Nicolau, Maria Fernanda Lopez-Ornelas, David Saah, Michael Brenner, Subhashini Venugopalan, and Sameera S Ponda. 2025. The Cloud-Based Geospatial Ben...

    2025

  25. [25]

    Alejandro Carrasco, Victor Rodriguez-Fernandez, and Richard Linares. 2025. Large language models as autonomous spacecraft operators in kerbal space program.Advances in Space Research76, 6 (2025), 3480–3497. doi:10.1016/j.asr.2025.06.034

    work page doi:10.1016/j.asr.2025.06.034 2025

  26. [26]

    Santiago Casas, Christian Fidler, Boris Bolliet, Francisco Villaescusa-Navarro, and Julien Lesgourgues. 2025. CLAPP: The CLASS LLM Agent for Pair Programming. arXiv:2508.05728 [astro-ph.IM] https://arxiv.org/abs/2508.05728

    arXiv 2025

  27. [27]

    Harry Caufield, Harshad Hegde, Vincent Emonet, et al

    J. Harry Caufield, Harshad Hegde, Vincent Emonet, et al. 2024. Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning.Bioinformatics40, 3 (2024), btae104. doi:10.1093/bioinformatics/btae104

    work page doi:10.1093/bioinformatics/btae104 2024

  28. [28]

    Ajenifujah, Janghoon Ock, and Amir Barati Farimani

    Achuth Chandrasekhara, Omid Barati Farimani, Olabode T. Ajenifujah, Janghoon Ock, and Amir Barati Farimani. 2025. NANOGPT: A Query- Driven Large Language Model Retrieval-Augmented Generation System for Nanotechnology Research.arXiv preprint arXiv:2502.20541(2025). doi:10.48550/arXiv.2502.20541

    work page doi:10.48550/arxiv.2502.20541 2025

  29. [29]

    Sreejato Chatterjee, Linh Tran, Quoc Duy Nguyen, Roni Kirson, Drue Hamlin, Harvest Aquino, Hanjia Lyu, Jiebo Luo, and Timothy Dye. 2025. Assessing Historical Structural Oppression Worldwide via Rule-Guided Prompting of Large Language Models.arXiv preprint arXiv:2509.15216 (2025)

    arXiv 2025

  30. [30]

    Bokai Chen, Weiwei Zheng, Liang Zhao, and Xiaojun Ding. 2025. Leveraging large language models to assist philosophical counseling: prospective techniques, value, and challenges.Humanities and Social Sciences Communications(2025). doi:10.1057/s41599-025-04657-7

    work page doi:10.1057/s41599-025-04657-7 2025

  31. [31]

    Chuke Chen, Nan Li, Jianchuan Qi, Huimin Chang, Wenjie Shi, Jinliang Xie, Jiayi Yuan, Hang Yang, Jing Guo, Changqing Xu, and Ming Xu

  32. [32]

    Leveraging LLMs for Environmental Complexity: Structured Fine-Tuning Data Sets and Deployment Strategies.Environmental Science & Technology60, 1 (2025)

    2025

  33. [33]

    Cheng-Yeh Chen and Raghupathy Sivakumar. 2026. The Mind’s Transformer: Computational Neuroanatomy of LLM-Brain Alignment. InThe Fourteenth International Conference on Learning Representations. https://openreview.net/forum?id=PgIlCCNxdB

    2026

  34. [34]

    Danlu Chen et al. 2024. LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP. In Findings of the Association for Computational Linguistics: EMNLP 2024. https://arxiv.org/abs/2408.04628

    arXiv 2024

  35. [35]

    Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, and Benyou Wang. 2025. Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems. InFindings of the Association for Computational Linguistics: ACL 2025 / preprint arXiv:2412.18925, Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar (...

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.18653/v1/2025.findings-acl.751 2025

  36. [36]

    Liuqing Chen, Qianzhi Jing, Yixin Tsang, Qianyi Wang, Lingyun Sun, and Jianxi Luo. 2024. DesignFusion: Integrating Generative Models for Conceptual Design Enrichment.Journal of Mechanical Design146, 11 (05 2024), 111703. doi:10.1115/1.4065487

    work page doi:10.1115/1.4065487 2024

  37. [37]

    Mouxiang Chen, Lei Zhang, Yunlong Feng, Xuwu Wang, Wenting Zhao, Ruisheng Cao, Jiaxi Yang, Jiawei Chen, Mingze Li, Zeyao Ma, Hao Ge, Zongmeng Zhang, Zeyu Cui, Dayiheng Liu, Jingren Zhou, Jianling Sun, Junyang Lin, and Binyuan Hui. 2026. SWE-Universe: Scale Real-World Verifiable Environments to Millions. arXiv:2602.02361 [cs.SE] https://arxiv.org/abs/2602....

    arXiv 2026

  38. [38]

    Wei Chen, Han Ding, Meng Yuan, Zhao Zhang, Deqing Wang, and Fuzhen Zhuang. 2025. Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive Alignment.arXiv preprint arXiv:2503.13879(2025). https://arxiv.org/pdf/2503.13879

    arXiv 2025

  39. [39]

    Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. 2022. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks.arXiv preprint arXiv:2211.12588(2022)

    Pith/arXiv arXiv 2022

  40. [40]

    Zhiyu Chen, Yujie Lu, and William Wang. 2023. Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting. InFindings of the Association for Computational Linguistics: EMNLP 2023, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, Singapore, 4295–4304....

    work page doi:10.18653/v1/2023.findings-emnlp.284 2023

  41. [41]

    Zhou Chen, Xiao Wang, Xinan Zhang, Ming Lin, Yuanhong Liao, Juanzi Li, and Yuqi Bai. 2025. GeoFactory: an LLM performance enhancement framework for geoscience factual and inferential tasks.Big Earth Data9, 4 (2025), 714–746. doi:10.1080/20964471.2025.2506291

    work page doi:10.1080/20964471.2025.2506291 2025

  42. [42]

    Zi-Yi Chen, Fan-Kai Xie, Meng Wan, Yang Yuan, Miao Liu, Zong-Guo Wang, Sheng Meng, and Yan-Gang Wang. 2023. MatChat: A large language model and application service platform for materials science.Chinese Physics B32, 11 (nov 2023), 118104. doi:10.1088/1674-1056/ad04cb

    work page doi:10.1088/1674-1056/ad04cb 2023

  43. [43]

    Yuheng Cheng, Huan Zhao, Xiyuan Zhou, Junhua Zhao, Yuji Cao, Chao Yang, and Xinlei Cai. 2025. A large language model for advanced power dispatch.Scientific Reports15, 1 (2025), 8925

    2025

  44. [44]

    Byounggook Cho, Gi-Young Lee, Junghyun Jung, Junyeop Kim, GunHo Park, Patrick C. N. Martin, Hyobin Kim, Jeein Oh, Jong-Soo Kim, Jongpil Kim, Tae-Hyung Kim, and Kyoung-Jae Won. 2026. PersonaAI: An Interactive Agentic-AI Framework for Autonomous Hypothesis Generation and Validation in Aging.bioRxiv(2026). doi:10.64898/2026.01.16.699755

    work page doi:10.64898/2026.01.16.699755 2026

  45. [45]

    Kamal Choudhary. 2025. DiffractGPT: Atomic Structure Determination from X-ray Diffraction Patterns Using a Generative Pretrained Transformer. Journal of Physical Chemistry Letters(2025). doi:10.1021/acs.jpclett.4c03137

    work page doi:10.1021/acs.jpclett.4c03137 2025

  46. [46]

    Yu, and Qingsong Wen

    Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, and Qingsong Wen. 2025. LLM Agents for Education: Advances and Applications. InFindings of the Association for Computational Linguistics: EMNLP 2025, Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, and Violet Peng (Eds.)...

    work page doi:10.18653/v1/2025.findings-emnlp.743 2025

  47. [47]

    Daniel J H Chung, Zhiqi Gao, Yurii Kvasiuk, Tianyi Li, Moritz Münchmeyer, Maja Rudolph, Frederic Sala, and Sai Chaitanya Tadepalli. 2025. Theoretical physics benchmark (TPBench)—a dataset and study of AI reasoning capabilities in theoretical physics.Machine Learning: Science and Technology6, 3 (sep 2025), 030505. doi:10.1088/2632-2153/adfcb0

    work page doi:10.1088/2632-2153/adfcb0 2025

  48. [48]

    Sergio Cruzes. 2025. Revolutionizing optical networks: The integration and impact of large language models.Optical Switching and Networking57 (2025), 100812

    2025

  49. [49]

    Albert, Pranesh Srinivasan, Haining Pan, Philippe Faist, Brian Rohr, Ekin Dogus Cubuk, Muratahan Aykol, Amil Merchant, Michael J

    Hao Cui, Zahra Shamsi, Gowoon Cheon, Xuejian Ma, Shutong Li, Maria Tikhanovskaya, Peter Norgaard, Nayantara Mudur, Martyna Plomecka, Paul Raccuglia, Yasaman Bahri, Victor V. Albert, Pranesh Srinivasan, Haining Pan, Philippe Faist, Brian Rohr, Ekin Dogus Cubuk, Muratahan Aykol, Amil Merchant, Michael J. Statt, Dan Morris, Drew Purves, Elise Kleeman, Ruth A...

    arXiv 2025

  50. [50]

    Yiming Cui, X Yao, Y Qin, et al. 2025. Evaluating large language models on multimodal chemistry olympiad exams.Communications Chemistry (2025). doi:10.1038/s42004-025-01782-x

    work page doi:10.1038/s42004-025-01782-x 2025

  51. [51]

    Chongyuan Dai, Jinpeng Hu, Hongchang Shi, Zhuo Li, Xun Yang, and Meng Wang. 2025. Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning. arXiv:2508.10848 [cs.CL] https://arxiv.org/abs/2508.10848

    arXiv 2025

  52. [52]

    Xi Dai, Yu Xi, Yong Hu, Qingyan Zhao, and Chaoxue Zhang. 2025. LLM Evaluation for Thyroid Nodule Assessment: Comparing ACR-TIRADS, C-TIRADS, and Clinician-AI Trust Gap.Frontiers in Endocrinology16 (2025), 1667809. doi:10.3389/fendo.2025.1667809

    work page doi:10.3389/fendo.2025.1667809 2025

  53. [53]

    Anurag Das, David Kerr, Namino Glantz, Wendy Bevier, Rony Santiago, Ricardo Gutierrez-Osuna, and Bobak Mortazavi. 2025. CGMacros: a pilot scientific dataset for personalized nutrition and diet monitoring.Scientific Data12 (09 2025). doi:10.1038/s41597-025-05851-7

    work page doi:10.1038/s41597-025-05851-7 2025

  54. [54]

    Mattia De Cao et al. 2024. Deep Learning Meets Egyptology: a Hieroglyphic Transformer for Translating Ancient Egyptian. InProceedings of the 1st Workshop on Machine Learning for Ancient Languages. Association for Computational Linguistics. https://aclanthology.org/2024.ml4al-1.9v1.pdf

    2024

  55. [55]

    Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal, Tuan Dung Nguyen, Alberto Accomazzi, Emily Herron, Vanessa Lama, Rui Pan, Azton Wells, and Nesar Ramachandra. 2025. AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model. arXiv:2505.17592 [astro-ph.IM] https://arxiv.org/abs/2505.17592

    arXiv 2025

  56. [56]

    Andrea Gregor de Varda, Ferdinando Pio D’Elia, Hope Kean, Andrew Lampinen, and Evelina Fedorenko. 2025. The cost of thinking is similar between large reasoning models and humans.Proceedings of the National Academy of Sciences122, 47 (2025), e2520077122

    2025

  57. [57]

    DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, et al. 2025. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models. arXiv:2512.02556 [cs.CL] https://arxiv.org/abs/2512.02556

    Pith/arXiv arXiv 2025

  58. [58]

    Cheng Deng, Tianhang Zhang, Zhongmou He, Yi Xu, Qiyuan Chen, Yuanyuan Shi, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin, and Junxian He. 2023. K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization. arXiv:2306.05064 doi:10.48550/arXiv.2306.05064 Project page notes acceptance to WSDM 2024 (ACM DOI may be 1...

    work page doi:10.48550/arxiv.2306.05064 2023

  59. [59]

    Gebauer, Henry Alexander Bradley, Dawid Maciorowski, Bria Persaud, Jordan Despanie, et al

    Sunishchal Dev, Charles Teague, Grant Ellison, Kyle Brady, Jeffrey Lee, Sarah L. Gebauer, Henry Alexander Bradley, Dawid Maciorowski, Bria Persaud, Jordan Despanie, et al. 2025.Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models. Research Report RRA3797-1. RAND Corporation. 20 Ferdinan et al

    2025

  60. [60]

    González-Castaño

    Francisco de Arriba Pérez, Silvia García-Méndez, Javier Otero-Mosquera, and Francisco J. González-Castaño. 2024. Explainable cognitive decline detection in free dialogues with a Machine Learning approach based on pre-trained Large Language Models.Applied Intelligence54, 24 (Sept. 2024), 12613–12628. doi:10.1007/s10489-024-05808-0

    work page doi:10.1007/s10489-024-05808-0 2024

  61. [61]

    Mehak Preet Dhaliwal, Andong Hua, Laya Pullela, Ryan Burke, and Yao Qin. 2025. NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions. InThe Thirteenth International Conference on Learning Representations. https://openreview.net/ forum?id=6LtdZCyuZR

    2025

  62. [62]

    Zhehao Dong, Zhen Lu, and Yue Yang. 2025. Fine-tuning a large language model for automating computational fluid dynamics simulations. Theoretical and Applied Mechanics Letters15, 3 (may 2025), 100594. doi:10.1016/j.taml.2025.100594

    work page doi:10.1016/j.taml.2025.100594 2025

  63. [63]

    Filip Dorm, Joseph Millard, Drew Purves, Michael Harfoot, and Oisin Mac Aodha. 2025. Large language models possess some ecological knowledge, but how much?bioRxiv(2025). doi:10.1101/2025.02.10.637097

    work page doi:10.1101/2025.02.10.637097 2025

  64. [64]

    Dornath, Aditya Balu, Adarsh Krishnamurthy, Asheesh K

    A. Dornath, Aditya Balu, Adarsh Krishnamurthy, Asheesh K. Singh, Arti Singh, Baskar Ganapathysubramanian, Chinmay Hegde, and Soumik Sarkar. 2025. Towards Large Reasoning Models for Agriculture.arXiv preprint arXiv:2505.19259(2025). https://arxiv.org/abs/2505.19259

    arXiv 2025

  65. [65]

    Gardner, and Hao ‘Frank’ Yang

    Hongru Du, Yang Zhao, Jianan Zhao, Shaochong Xu, Xihong Lin, Yiran Chen, Lauren M. Gardner, and Hao ‘Frank’ Yang. 2025. Advancing real-time infectious disease forecasting using large language models.Nature Computational Science5, 6 (01 Jun 2025), 467–480. doi:10.1038/s43588-025-00798-6

    work page doi:10.1038/s43588-025-00798-6 2025

  66. [66]

    Mengge Du, Yuntian Chen, Zhongzheng Wang, Longfeng Nie, and Dongxiao Zhang. 2024. Large language models for automatic equation discovery of nonlinear dynamics.Physics of Fluids36, 9 (09 2024), 097121. doi:10.1063/5.0224297

    work page doi:10.1063/5.0224297 2024

  67. [67]

    Plasek, Ya-Wen Chuang, Liqin Wang, Gad A

    Xinsong Du, John Novoa-Laurentiev, Joseph M. Plasek, Ya-Wen Chuang, Liqin Wang, Gad A. Marshall, Stephanie K. Mueller, Frank Chang, Surabhi Datta, Hunki Paek, Bin Lin, Qiang Wei, Xiaoyan Wang, Jingqi Wang, Hao Ding, Frank J. Manion, Jingcheng Du, David W. Bates, and Li Zhou. 2024. Enhancing early detection of cognitive decline in the elderly: a comparativ...

    work page doi:10.1016/j.ebiom.2024.105401 2024

  68. [68]

    Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv:2404.16130 [cs.CL] https://arxiv.org/abs/2404.16130

    Pith/arXiv arXiv 2025

  69. [69]

    Ehrlich-Sommer, B

    F. Ehrlich-Sommer, B. Eberhard, and A. Holzinger. 2025. ForestGPT and Beyond: A Trustworthy Domain-Specific Large Language Model Paving the Way to Forestry 5.0.Electronics14, 18 (2025), 3583. https://www.mdpi.com/2079-9292/14/18/3583

    2025

  70. [70]

    Morris, Chun-Cheng Chang, Xuhai "Orson" Xu, Lianhui Qin, Daniel McDuff, Xin Liu, Shwetak Patel, and Vikram Iyer

    Zachary Englhardt, Chengqian Ma, Margaret E. Morris, Chun-Cheng Chang, Xuhai "Orson" Xu, Lianhui Qin, Daniel McDuff, Xin Liu, Shwetak Patel, and Vikram Iyer. 2024. From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol...

    work page doi:10.1145/3659604 2024

  71. [71]

    European Research Council. 2025. Panel Chairs – ERC Starting Grant 2026. https://erc.europa.eu/system/files/2025-10/Panel_Chairs_ERC_ Starting_Grant_2026.pdf. Accessed: 2026-02-11

    2025

  72. [72]

    Maddison, and BO WANG

    Adibvafa Fallahpour, Andrew Magnuson, Purav Gupta, Shihao Ma, Jack Naimer, Arnav Shah, Haonan Duan, Omar Ibrahim, Hani Goodarzi, Chris J. Maddison, and BO WANG. 2025. BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?i...

    2025

  73. [73]

    Ka Siu Fan, Jeffrey Gan, Isabelle Zou, Maja Kaladjiska, Monique Borg Inguanez, and Gillian Garden. 2025. Poor Performance of Large Language Models Based on the Diabetes and Endocrinology Specialty Certificate Examination of the United Kingdom.Cureus17 (10 2025). doi:10.7759/ cureus.93960

    2025

  74. [74]

    Yin Fang, Qiao Jin, Guangzhi Xiong, Bowen Jin, Xianrui Zhong, Siru Ouyang, Aidong Zhang, Jiawei Han, and Zhiyong Lu. 2025. Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning. arXiv:2506.02911 [cs.CL] https://arxiv.org/abs/2506.02911

    arXiv 2025

  75. [75]

    Adams, Felix Busch, Conor Fallon, Marc Huppertz, Robert Siepmann, Philipp Prucker, Nadine Bayerl, Daniel Truhn, Marcus Makowski, Alexander Löser, and Keno K

    Dennis Fast, Lisa C. Adams, Felix Busch, Conor Fallon, Marc Huppertz, Robert Siepmann, Philipp Prucker, Nadine Bayerl, Daniel Truhn, Marcus Makowski, Alexander Löser, and Keno K. Bressem. 2024. Autonomous medical evaluation for guideline adherence of large language models.npj Digital Medicine7 (2024), 358. doi:10.1038/s41746-024-01356-6

    work page doi:10.1038/s41746-024-01356-6 2024

  76. [76]

    Daniel Fein, Sebastian Russo, Violet Xiang, Kabir Jolly, Rafael Rafailov, and Nick Haber. 2025. LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing.arXiv preprint arXiv:2507.00769(2025). doi:10.48550/arXiv.2507.00769

    work page doi:10.48550/arxiv.2507.00769 2025

  77. [77]

    Kaiyue Feng, Yilun Zhao, Yixin Liu, Tianyu Yang, Chen Zhao, John Sous, and Arman Cohan. 2025. Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving. InFindings of the Association for Computational Linguistics: ACL 2025, Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar (Eds.). Association for Computa...

    work page doi:10.18653/v1/2025.findings-acl.610 2025

  78. [78]

    Yichun Feng, Lu Zhou, Chao Ma, Yikai Zheng, Ruikun He, and Yixue Li. 2025. Knowledge graph–based thought: a knowledge graph–enhanced LLM framework for pan-cancer question answering.GigaScience14 (2025). doi:10.1093/gigascience/giae082

    work page doi:10.1093/gigascience/giae082 2025

  79. [79]

    Jingru Gan, Peichen Zhong, Yuanqi Du, Yanqiao Zhu, Chenru Duan, Haorui Wang, Daniel Schwalbe-Koda, Carla P Gomes, Kristin A Persson, and Wei Wang. 2025. MatLLMSearch: Crystal Structure Discovery with Evolution-Guided Large Language Models.arXiv preprint arXiv:2502.20933 (2025)

    arXiv 2025

  80. [80]

    Kanishk Gandhi, J.-Philipp Fränken, Tobias Gerstenberg, and Noah D. Goodman. 2023. Understanding social reasoning in language models with language models. InProceedings of the 37th International Conference on Neural Information Processing Systems(New Orleans, LA, USA)(NIPS ’23). Curran Associates Inc., Red Hook, NY, USA, Article 595, 12 pages. Reasoning4S...

    2023

Showing first 80 references.