{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T19:39:32Z","timestamp":1792438772040,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA0480201"],"award-info":[{"award-number":["XDA0480201"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818869","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"12195-12206","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2970-7575","authenticated-orcid":false,"given":"Boxiao","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3840-3270","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4375-0987","authenticated-orcid":false,"given":"Tianyi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Aerodynamics, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7526-5343","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Aerodynamics, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6485-9303","authenticated-orcid":false,"given":"Junzhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9190-3509","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1289-2758","authenticated-orcid":false,"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104085"},{"key":"e_1_3_2_1_2_1","unstructured":"Luca Biggio Tommaso Bendinelli Alexander Neitz Aurelien Lucchi and Giambattista Parascandolo. 2021. Neural Symbolic Regression that Scales. https:\/\/arxiv.org\/abs\/2106.06427"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of 38th International Conference on Machine Learning (ICML 2021)","volume":"945","author":"L.","unstructured":"L. Biggio*, T. Bendinelli*, A. Neitz, A. Lucchi, and G. Parascandolo. 2021. Neural Symbolic Regression that Scales. In Proceedings of 38th International Conference on Machine Learning (ICML 2021) (Proceedings of Machine Learning Research, Vol. 139). PMLR, 936-945. https:\/\/proceedings.mlr.press\/v139\/biggio21a.html"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Representation Learning","author":"Chen Jindou","year":"2025","unstructured":"Jindou Chen, Jidong Tian, Liang Wu, ChenXin Wei, Xiaokang Yang, Yaohui Jin, and Yanyan Xu. 2025. KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics. In International Conference on Representation Learning, Y. Yue, A. Garg, N. Peng, F. Sha, and R. Yu (Eds.), Vol. 2025. 67058-67080. https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/a76b693f36916a5ed84d6e5b39a0dc03-Paper-Conference.pdf"},{"key":"e_1_3_2_1_5_1","unstructured":"Miles Cranmer. 2023. Interpretable Machine Learning for Science with PySR and Symbolic Regression.jl. https:\/\/arxiv.org\/abs\/2305.01582"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/849"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.109010"},{"key":"e_1_3_2_1_8_1","volume-title":"DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement learning. https:\/\/arxiv.org\/abs\/2210.02181","author":"Du Mengge","year":"2023","unstructured":"Mengge Du, Yuntian Chen, and Dongxiao Zhang. 2023. DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement learning. https:\/\/arxiv.org\/abs\/2210.02181"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118723203"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Arya Grayeli Atharva Sehgal Omar Costilla-Reyes Miles Cranmer and Swarat Chaudhuri. 2024. Symbolic Regression with a Learned Concept Library. https:\/\/arxiv.org\/abs\/2409.09359","DOI":"10.52202\/079017-1419"},{"key":"e_1_3_2_1_11_1","unstructured":"Ping Guo Qingfu Zhang and Xi Lin. 2025. CoEvo: Continual Evolution of Symbolic Solutions Using Large Language Models. https:\/\/arxiv.org\/abs\/2412.18890"},{"key":"e_1_3_2_1_12_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_13_1","volume-title":"CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design. https:\/\/arxiv.org\/abs\/2505.12285","author":"Huang Ziyao","year":"2025","unstructured":"Ziyao Huang, Weiwei Wu, KuiWu, Jianping Wang, and Wei-Bin Lee. 2025. CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design. https:\/\/arxiv.org\/abs\/2505.12285"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Pierre-Alexandre Kamienny St\u00e9phane d'Ascoli Guillaume Lample and Fran\u00e7ois Charton. 2022. End-to-end symbolic regression with transformers. https:\/\/arxiv.org\/abs\/2204.10532","DOI":"10.52202\/068431-0746"},{"key":"e_1_3_2_1_15_1","unstructured":"Paul Kassianik Baturay Saglam Alexander Chen Blaine Nelson Anu Vellore Massimo Aufiero Fraser Burch Dhruv Kedia Avi Zohary SajanaWeerawardhena Aman Priyanshu Adam Swanda Amy Chang Hyrum Anderson Kojin Oshiba Omar Santos Yaron Singer and Amin Karbasi. 2025. Llama-3.1-FoundationAISecurityLLM-Base-8B Technical Report. https:\/\/arxiv.org\/abs\/2504.21039"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"J.R. Koza. 1990. Genetically breeding populations of computer programs to solve problems in artificial intelligence. In [1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence. 819-827. doi:10.1109\/TAI.1990.130444","DOI":"10.1109\/TAI.1990.130444"},{"key":"e_1_3_2_1_17_1","first-page":"33985","volume-title":"Oh (Eds.)","volume":"35","author":"Landajuela Mikel","year":"2022","unstructured":"Mikel Landajuela, Chak Shing Lee, Jiachen Yang, Ruben Glatt, Claudio P Santiago, Ignacio Aravena, Terrell Mundhenk, Garrett Mulcahy, and Brenden K Petersen. 2022. A Unified Framework for Deep Symbolic Regression. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 33985-33998. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/dbca58f35bddc6e4003b2dd80e42f838-Paper-Conference.pdf"},{"key":"e_1_3_2_1_18_1","volume-title":"Faissol","author":"Landajuela Mikel","year":"2021","unstructured":"Mikel Landajuela, Brenden K. Petersen, Soo K. Kim, Claudio P. Santiago, Ruben Glatt, T. Nathan Mundhenk, Jacob F. Pettit, and Daniel M. Faissol. 2021. Improving exploration in policy gradient search: Application to symbolic optimization. https:\/\/arxiv.org\/abs\/2107.09158"},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:259298765","author":"Li Wenqiang","year":"2023","unstructured":"Wenqiang Li, Weijun Li, Linjun Sun, Min Wu, Lina Yu, Jingyi Liu, Yanjie Li, and Song Tian. 2023. Transformer-based model for symbolic regression via joint supervised learning. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:259298765"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"33962","author":"Ma Pingchuan","year":"2024","unstructured":"Pingchuan Ma, Tsun-Hsuan Wang, Minghao Guo, Zhiqing Sun, Joshua B. Tenenbaum, Daniela Rus, Chuang Gan, and Wojciech Matusik. 2024. LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 33940-33962. https:\/\/proceedings.mlr.press\/v235\/ma24m.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/pnasnexus\/pgae467"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10622-0"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.2514\/3.12149"},{"key":"e_1_3_2_1_24_1","unstructured":"Florian R Menter Martin Kuntz Robin Langtry et al. 2003. Ten years of industrial experience with the SST turbulence model. Turbulence heat and mass transfer 4 1 (2003) 625-632."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-srw.49"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1299\/kikaib.66.646_1309"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2021.924"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.mi.03.100149.002103"},{"key":"e_1_3_2_1_29_1","volume-title":"Petersen","author":"Mundhenk T. Nathan","year":"2021","unstructured":"T. Nathan Mundhenk, Mikel Landajuela, Ruben Glatt, Claudio P. Santiago, Daniel M. Faissol, and Brenden K. Petersen. 2021. Symbolic Regression via Neural-Guided Genetic Programming Population Seeding. https:\/\/arxiv.org\/abs\/2111.00053"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1083142.1083143"},{"key":"e_1_3_2_1_31_1","volume-title":"Kim","author":"Petersen Brenden K.","year":"2021","unstructured":"Brenden K. Petersen, Mikel Landajuela, T. Nathan Mundhenk, Claudio P. Santiago, Soo K. Kim, and Joanne T. Kim. 2021. Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients. https:\/\/arxiv.org\/abs\/1912.04871"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Stephen B. Pope. 2000. Turbulent Flows. Cambridge University Press. doi:10.1017\/cbo9780511840531","DOI":"10.1017\/cbo9780511840531"},{"key":"e_1_3_2_1_33_1","unstructured":"Julien Pourcel C\u00e9dric Colas and Pierre-Yves Oudeyer. 2025. Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARCAGI. https:\/\/arxiv.org\/abs\/2507.14172"},{"key":"e_1_3_2_1_34_1","first-page":"36","article-title":"Graph Networks as Inductive Bias for Genetic Programming: Symbolic Models for Particle-Laden Flows. In Genetic Programming, Gisele Pappa, Mario Giacobini, and Zdenek Vasicek (Eds.). Springer Nature Switzerland","author":"Reuter Julia","year":"2023","unstructured":"Julia Reuter, Hani Elmestikawy, Fabien Evrard, Sanaz Mostaghim, and Berend van Wachem. 2023. Graph Networks as Inductive Bias for Genetic Programming: Symbolic Models for Particle-Laden Flows. In Genetic Programming, Gisele Pappa, Mario Giacobini, and Zdenek Vasicek (Eds.). Springer Nature Switzerland, Cham, 36-51.","journal-title":"Cham"},{"key":"e_1_3_2_1_35_1","volume-title":"Jordan S Ellenberg, Pengming Wang, Omar Fawzi, et al.","author":"Romera-Paredes Bernardino","year":"2024","unstructured":"Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M Pawan Kumar, Emilien Dupont, Francisco JR Ruiz, Jordan S Ellenberg, Pengming Wang, Omar Fawzi, et al. 2024. Mathematical discoveries from program search with large language models. Nature 625, 7995 (2024), 468-475."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1128\/aem.61.2.610-616.1995"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1165893"},{"key":"e_1_3_2_1_38_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_1_39_1","unstructured":"Hao Shi Weili Song Xinting Zhang Jiahe Shi Cuicui Luo Xiang Ao Hamid Arian and Luis Seco. 2024. AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors. https:\/\/arxiv.org\/abs\/2406.18394"},{"key":"e_1_3_2_1_40_1","volume-title":"Amir Barati Farimani, and Chandan K Reddy","author":"Shojaee Parshin","year":"2025","unstructured":"Parshin Shojaee, Kazem Meidani, Shashank Gupta, Amir Barati Farimani, and Chandan K Reddy. 2025. LLM-SR: Scientific Equation Discovery via Programming with Large Language Models. https:\/\/arxiv.org\/abs\/2404.18400"},{"key":"e_1_3_2_1_41_1","volume-title":"Khoa D Doan, and Chandan K Reddy.","author":"Shojaee Parshin","year":"2025","unstructured":"Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani, Amir Barati Farimani, Khoa D Doan, and Chandan K Reddy. 2025. LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models. https:\/\/arxiv.org\/abs\/2504.10415"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0135638"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0135638"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3014.001.0001"},{"key":"e_1_3_2_1_45_1","unstructured":"Mojtaba Valipour Bowen You Maysum Panju and Ali Ghodsi. 2021. SymbolicGPT: A Generative Transformer Model for Symbolic Regression. https: \/\/arxiv.org\/abs\/2106.14131"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3374649"},{"key":"e_1_3_2_1_47_1","volume-title":"Pissis","author":"Virgolin Marco","year":"2022","unstructured":"Marco Virgolin and Solon P. Pissis. 2022. Symbolic Regression is NP-hard. https:\/\/arxiv.org\/abs\/2207.01018"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10928-023-09887-3"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.7638\/kqdlxxb-2016.0158"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.168744"},{"key":"e_1_3_2_1_51_1","unstructured":"Shijie Xia Yuhan Sun and Pengfei Liu. 2025. SR-Scientist: Scientific Equation Discovery With Agentic AI. https:\/\/arxiv.org\/abs\/2510.11661"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2020.104431"},{"key":"e_1_3_2_1_53_1","volume-title":"RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NdHka08uWn","author":"Zhang Hengzhe","year":"2025","unstructured":"Hengzhe Zhang, Qi Chen, Bing XUE, Wolfgang Banzhaf, and Mengjie Zhang. 2025. RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NdHka08uWn"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:23:02Z","timestamp":1786065782000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":53,"alternative-id":["10.1145\/3770855.3818869","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818869","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}