{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:04:36Z","timestamp":1791486276112,"version":"4.3.4"},"reference-count":92,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"6820","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Science"],"published-print":{"date-parts":[[2026,10,8]]},"abstract":"<jats:p>Large language models (LLMs) increasingly excel at mathematics tasks, but their unreliability limits their utility in mathematics research. A mitigation is to use LLMs to generate formal proofs in languages such as Lean, in which the compiler verifies every proof step. We present the first demonstration of this method\u2019s value in solving open problems at scale. We built an artificial intelligence agent for formal proof search that autonomously resolved nine of 353 open Erd\u0151s problems, proved 44\/492 On-Line Encyclopedia of Integer Sequences conjectures, and is being deployed in combinatorics, optimization, graph theory, algebraic geometry, and quantum optics research. Even a basic agent alternating LLM-based generation with Lean-based verification replicated the Erd\u0151s successes. These findings demonstrate the power of formal proof search as an enabler of autonomous mathematical discovery.<\/jats:p>","DOI":"10.1126\/science.aej2213","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:00:31Z","timestamp":1791482431000},"page":"234-239","update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Advancing mathematics research with AI-driven formal proof search"],"prefix":"10.1126","volume":"394","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8938-2487","authenticated-orcid":true,"given":"George","family":"Tsoukalas","sequence":"first","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9011-6729","authenticated-orcid":true,"given":"Anton","family":"Kovsharov","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1653-4783","authenticated-orcid":true,"given":"Sergey","family":"Shirobokov","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9695-3441","authenticated-orcid":true,"given":"Anja","family":"Surina","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moritz","family":"Firsching","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1338-1346","authenticated-orcid":true,"given":"Gergely","family":"B\u00e9rczi","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Aarhus University, Aarhus, Denmark."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco J. R.","family":"Ruiz","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4113-5924","authenticated-orcid":true,"given":"Arun","family":"Suggala","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam Zsolt","family":"Wagner","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0412-4978","authenticated-orcid":true,"given":"Eric","family":"Wieser","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8303-3674","authenticated-orcid":true,"given":"Lei","family":"Yu","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2476-9194","authenticated-orcid":true,"given":"Aja","family":"Huang","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6928-7423","authenticated-orcid":true,"given":"Mikl\u00f3s Z.","family":"Horv\u00e1th","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8892-2610","authenticated-orcid":true,"given":"Andrew","family":"Ferraiuolo","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henryk","family":"Michalewski","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2479-0073","authenticated-orcid":true,"given":"Codrut","family":"Grosu","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edward","family":"Lockhart","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-3933","authenticated-orcid":true,"given":"Thomas","family":"Hubert","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5552-9855","authenticated-orcid":true,"given":"Matej","family":"Balog","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7466-7997","authenticated-orcid":true,"given":"Pushmeet","family":"Kohli","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6859-1391","authenticated-orcid":true,"given":"Swarat","family":"Chaudhuri","sequence":"additional","affiliation":[{"name":"Google DeepMind, London, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","unstructured":"T. Feng T. H. Trinh G. Bingham D. Hwang Y. Chervonyi J. Jung J. Lee C. Pagano S.-h. Kim F. Pasqualotto S. Gukov J. N. Lee J. Kim K. Hou G. Ghiasi Y. Tay Y. Li C. Kuang Y. Liu H. Lin E. Z. Liu N. Nayakanti X. Yang H.-t. Cheng D. Hassabis K. Kavukcuoglu Q. V. Le T. Luong Towards autonomous mathematics research. arXiv.2602.10177 [cs.LG] (2026)."},{"key":"e_1_3_2_3_2","unstructured":"V. Cohen-Addad L. Jain J. Mao S. Zuo M. Bateni S. Branzei M. P. Brenner L. Chen Y. Feng L. Fortnow G. Fu Z. Guan Z. Hadizadeh M. T. Hajiaghayi M. J. Raviz A. Javanmard C. S. Karthik K.-I. Kawarabayashi R. Kumar S. Lattanzi E. Lee Y. Li I. Panageas D. Paparas B. Przybocki B. Subercaseaux O. Svensson S. Taherijam X. Wu E. Yogev M. Zadimoghaddam S. Zhou J. Manyika V. Mirrokni Accelerating scientific research with Gemini: Case studies and common techniques. arXiv.2602.03837 [cs.CC] (2026)."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1006\/jcta.2000.3142"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"T. Achim A. Best A. Bietti K. Der M. F\u00e9d\u00e9rico S. Gukov D. Halpern-Leister K. Henningsgard Y. Kudryashov A. Meiburg M. Michelsen R. Patterson E. Rodriguez L. Scharff V. Shanker V. Sicca H. Sowrirajan A. Swope M. Tamas V. Tenev J. Thomm H. Williams L. Wu Aristotle: IMO-level automated theorem proving. arXiv.2510.01346 [cs.AI] (2025).","DOI":"10.70777\/si.v3i3.18745"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-79876-5_37"},{"key":"e_1_3_2_7_2","unstructured":"S. Hariharan C. Birkbeck S. Lee H. K. G. Ma B. Mehta A. Poiroux M. Viazovska A milestone in formalization: The sphere packing problem in dimension 8. arXiv.2604.23468 [math.MG] (2026)."},{"key":"e_1_3_2_8_2","unstructured":"A. Novikov N. V\u0169 M. Eisenberger E. Dupont P.-S. Huang A. Z. Wagner S. Shirobokov B. Kozlovskii F. J. R. Ruiz A. Mehrabian M. P. Kumar A. See S. Chaudhuri G. Holland A. Davies S. Nowozin P. Kohli M. Balog AlphaEvolve: A coding agent for scientific and algorithmic discovery. arXiv.2506.13131 [cs.LG] (2025)."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1006\/jcta.2000.3142"},{"key":"e_1_3_2_10_2","first-page":"A13","article-title":"A note on P-sets","volume":"4","author":"Baier S.","year":"2004","unstructured":"S. Baier, A note on P-sets. Integers 4, A13 (2004).","journal-title":"Integers"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00605-016-0995-9"},{"key":"e_1_3_2_12_2","unstructured":"B. Green \u201c100 open problems\u201d (University of Oxford 2024); https:\/\/people.maths.ox.ac.uk\/greenbj\/papers\/open-problems.pdf."},{"key":"e_1_3_2_13_2","unstructured":"A. Ferraiuolo E. Wieser google-deepmind\/alphaproof-nexus-results: v1.0.0-science-submission Zenodo (2026); https:\/\/doi.org\/10.5281\/zenodo.21477349."},{"key":"e_1_3_2_14_2","unstructured":"G. Huntley Ralph Wiggum as a \u201csoftware engineer\u201d (2025); https:\/\/ghuntley.com\/ralph."},{"key":"e_1_3_2_15_2","volume-title":"International Conference on Machine Learning","author":"Hubert T.","year":"2021","unstructured":"T. Hubert, J. Schrittwieser, I. Antonoglou, M. Barekatain, S. Schmitt, D. Silver, Learning and planning in complex action spaces, in International Conference on Machine Learning (2021)."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"e_1_3_2_17_2","unstructured":"T. Bloom ErdosProblems.com (2026); https:\/\/www.erdosproblems.com."},{"key":"e_1_3_2_18_2","unstructured":"M. Firsching P. Lezeau S. Mercuri M. Z. Horv\u00e1th Y. Dillies C. S\u00f6nne E. Wieser F. Zhang T. Hubert B. Ag\u00fcera y Arcas P. Kohli Formal Conjectures: An open and evolving benchmark for verified discovery in mathematics. arXiv.2602.03837 [cs.AI] (2026)."},{"key":"e_1_3_2_19_2","unstructured":"T. Tao et al. teorth \/ erdosproblems Public (Github 2026); https:\/\/github.com\/teorth\/erdosproblems\/wiki\/AI-contributions-to-Erd."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1112\/plms\/s3-21.1.97"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.4064\/aa-77-2-133-138"},{"key":"e_1_3_2_22_2","unstructured":"N. J. Sloane The On-Line Encyclopedia of Integer Sequences in Proceedings of the 14th Symposium on Towards Mechanized Mathematical Assistants: 6th International Conference Calculemus \u201907 \/ MKM \u201907 (Springer Berlin Heidelberg) (2007) p. 130.10.1007\/978-3-540-73086-6_12"},{"key":"e_1_3_2_23_2","unstructured":"E. K. Ryu K. Yuan W. Yin ODE analysis of stochastic gradient methods with optimism and anchoring for minimax problems. arXiv.1905.10899 [cs.LG] (2020)."},{"key":"e_1_3_2_24_2","unstructured":"A. Surina A. Suggala G. Tsoukalas A. Kovsharov S. Shirobokov F. J. R. Ruiz P. Kohli S. Chaudhuri An improved last-iterate convergence rate for Anchored Gradient Descent Ascent. arXiv.2604.03782 [math.OC] (2026)."},{"key":"e_1_3_2_25_2","unstructured":"Y. Cai W. Zheng Last-iterate convergence of Anchored Gradient Descent. arXiv.2604.12235 [math.OC] (2026)."},{"key":"e_1_3_2_26_2","unstructured":"S. M. Ulam A Collection of Mathematical Problems vol. 8 of Interscience Tracts in Pure and Applied Mathematics (Interscience Publishers 1960)."},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","unstructured":"S. Fajtlowicz \u201cOn Conjectures of Graffiti\u201d in Graph Theory and Applications J. Akiyama Y. Egawa H. Enomoto Eds. (Elsevier) vol. 38 of Annals of Discrete Mathematics pp. 113\u2013118 (1988).","DOI":"10.1016\/S0167-5060(08)70776-3"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1216\/jca.2024.16.245"},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"M. Boij J. C. Migliore R. M. Mir\u00f3-Roig U. Nagel F. Zanello On the Shape of a Pure O-Sequence vol. 218 of Memoirs of the American Mathematical Society (American Mathematical Society 2012).","DOI":"10.1090\/S0065-9266-2011-00647-7"},{"key":"e_1_3_2_30_2","unstructured":"A. J. de Jong The Stacks Project (Columbia University 2026); https:\/\/stacks.math.columbia.edu."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.119.240403"},{"key":"e_1_3_2_32_2","unstructured":"T. Feng J. Jung S.-h. Kim C. Pagano S. Gukov C.-C. Tsai D. Woodruff A. Javanmard A. Mokhtari D. Hwang Y. Chervonyi J. N. Lee G. Bingham T. H. Trinh V. Mirrokni Q. V. Le T. Luong Aletheia tackles FirstProof autonomously. arXiv.2602.21201 [cs.AI] (2026)."},{"key":"e_1_3_2_33_2","unstructured":"B. Alexeev M. Putterman M. Sawhney M. Sellke G. Valiant Short proofs in combinatorics probability and number theory II. arXiv.2604.06609 [math.CO] (2026)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"The Mathlib Community The Lean Mathematical Library in Proceedings of the 9th ACM SIGPLAN International Conference on Certified Programs and Proofs CPP 2020 (ACM New Orleans LA USA) (2020).10.1007\/978-3-540-73086-6_12","DOI":"10.1145\/3372885.3373824"},{"key":"e_1_3_2_35_2","unstructured":"GasStationManager SafeVerify (Github 2025); https:\/\/github.com\/GasStationManager\/SafeVerify."},{"key":"e_1_3_2_36_2","first-page":"193","article-title":"The Analysis of Permutations","volume":"24","author":"Plackett R. L.","year":"1975","unstructured":"R. L. Plackett, The Analysis of Permutations. J. R. Stat. Soc. Ser. C Appl. Stat. 24, 193\u2013202 (1975).","journal-title":"J. R. Stat. Soc. Ser. C Appl. Stat."},{"key":"e_1_3_2_37_2","volume-title":"Individual Choice Behavior: A Theoretical Analysis","author":"Luce R.","year":"1959","unstructured":"R. Luce, Individual Choice Behavior: A Theoretical Analysis (Wiley, 1959)."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2012.638220"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-90643-5_6"},{"key":"e_1_3_2_40_2","unstructured":"Math Inc Gauss: An agent for autoformalization (2026) https:\/\/www.math.inc\/gauss."},{"key":"e_1_3_2_41_2","volume-title":"International Conference on Machine Learning","author":"Yang K.","year":"2025","unstructured":"K. Yang, G. Poesia, J. He, W. Li, K. E. Lauter, S. Chaudhuri, D. Song, Position: Formal Mathematical Reasoning: A New Frontier in AI, in International Conference on Machine Learning (2025)."},{"key":"e_1_3_2_42_2","unstructured":"J. Chen W. Chen J. Du J. Hu Z. Jiang A. Jie X. Jin X. Jin C. Li W. Shi Z. Wang M. Wang C. Wei S. Wei H. Xin F. Yang W. Gao Z. Yuan T. Zhan Z. Zheng T. Zhou T. H. Zhu Seed-prover 1.5: Mastering undergraduate-level theorem proving via learning from experience. arXiv.2512.17260 [cs.CL] (2025)."},{"key":"e_1_3_2_43_2","unstructured":"DeepSeek-AI DeepSeek-V2: A Strong Economical and Efficient Mixture-of-Experts Language Model arXiv.2512.17260 [cs.CL] (2024)."},{"key":"e_1_3_2_44_2","unstructured":"H. Wang M. Unsal X. Lin M. Baksys J. Liu M. Dos Santos F. Sung M. Vinyes Z. Ying Z. Zhu J. Lu H. de Saxc\u00e9 B. Bailey C. Song C. Xiao D. Zhang E. Zhang F. Pu H. Zhu J. Liu J. Bayer J. Michel L. Yu L. Dreyfus-Schmidt L. Tunstall L. Pagani M. Machado P. Bourigault R. Wang S. Polu T. Barroyer W.-D. Li Y. Niu Y. Fleureau Y. Hu Z. Yu Z. Wang Z. Yang Z. Liu J. Li Kimina-prover preview: Towards large formal reasoning models with reinforcement learning. arXiv.2504.11354 [cs.AI] (2025)."},{"key":"e_1_3_2_45_2","volume-title":"International Conference on Learning Representations","author":"Lin Y.","year":"2026","unstructured":"Y. Lin, S. Tang, B. Lyu, Z. Yang, J.-H. Chung, H. Zhao, L. Jiang, Y. Geng, J. Ge, J. Sun, J. Wu, J. Gesi, X. Lu, D. Acuna, K. Yang, H. Lin, Y. Choi, D. Chen, S. Arora, C. Jin, Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction, in International Conference on Learning Representations (2026)."},{"key":"e_1_3_2_46_2","unstructured":"S. Polu I. Sutskever Generative language modeling for automated theorem proving. arXiv.2009.03393 [cs.LG] (2020)."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0608"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0944"},{"key":"e_1_3_2_49_2","volume-title":"International Conference on Learning Representations","author":"Jiang A. Q.","year":"2023","unstructured":"A. Q. Jiang, Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs, in International Conference on Learning Representations (2023)."},{"key":"e_1_3_2_50_2","volume-title":"International Conference on Learning Representations","author":"Varambally S.","year":"2026","unstructured":"S. Varambally., Hilbert: Recursively Building Formal Proofs with Informal Reasoning, in International Conference on Learning Representations (2026)."},{"key":"e_1_3_2_51_2","unstructured":"A. X. L. E. Axiom Axiom Lean Engine https:\/\/axle.axiommath.ai\/ (2025)."},{"key":"e_1_3_2_52_2","volume-title":"Conference on Language Models","author":"Thakur A.","year":"2024","unstructured":"A. Thakur, G. Tsoukalas, Y. Wen, J. X. Xin, S. Chaudhuri, An in-context learning agent for formal theorem-proving, in Conference on Language Models (2024)."},{"key":"e_1_3_2_53_2","unstructured":"P.-N. Kung L. Song D. Hwang J. Yoon C.-L. Li S. Severini M. Ol\u0161\u00e1k E. Lockhart Q. V. Le B. Gokturk T. Luong T. Pfister N. Peng LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks. arXiv.2606.03303 [cs.AI] (2026)."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9153.001.0001"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45949-9"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175355"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"e_1_3_2_58_2","unstructured":"B. Georgiev J. G\u00f3mez-Serrano T. Tao A. Z. Wagner Mathematical exploration and discovery at scale. arXiv.2511.02864 [cs.NE] (2025)."},{"key":"e_1_3_2_59_2","unstructured":"A. Nagda P. Raghavan A. Thakurta Reinforced generation of combinatorial structures: Ramsey numbers. arXiv preprint arXiv:2603.09172 (2026)."},{"key":"e_1_3_2_60_2","unstructured":"A. Nagda P. Raghavan A. Thakurta Reinforced generation of combinatorial structures: Ramsey numbers. arXiv.2603.09172 [math.CO] (2026)."},{"key":"e_1_3_2_61_2","unstructured":"D. Zheng I. von Glehn Y. Zwols I. Beloshapka L. Buesing D. M. Roy M. Wattenberg B. Georgiev T. Schmidt A. Cowie F. Viegas D. Kanevsky V. Kahlon H. Maennel S. Alj G. Holland A. Davies P. Kohli A. I. Co-Mathematician Accelerating Mathematicians with Agentic AI. arXiv.2605.06651 [cs.AI] (2026)."},{"key":"e_1_3_2_62_2","unstructured":"J. Bryan B. Elek F. Manners G. Salafatinos R. Vakil The motivic class of the space of genus 0 maps to the flag variety. arXiv.2601.07222 [math.AG] (2026)."},{"key":"e_1_3_2_63_2","unstructured":"Google DeepMind Gemini 3.1 Deep Think (2026) https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_3_deep_think_model_evaluation.pdf."},{"key":"e_1_3_2_64_2","unstructured":"B. Alexeev M. Putterman M. Sawhney M. Sellke G. Valiant Short proofs in combinatorics and number theory. arXiv.2603.29961 [math.CO] (2026)."},{"key":"e_1_3_2_65_2","unstructured":"B. Alexeev K. Barreto Y. Li J. D. Lichtman L. Price J. I. Shah Q. Tang T. Tao Primitive sets and von Mangoldt chains: Erd\u0151s Problem #1196 and beyond. arXiv.2605.00301 [math.NT] (2026)."},{"key":"e_1_3_2_66_2","unstructured":"U. Jang E. K. Ryu Point Convergence of Nesterov\u2019s Accelerated Gradient Method: An AI-Assisted Proof. arXiv.2510.23513 [math.OC] (2025)."},{"key":"e_1_3_2_67_2","unstructured":"J. Schmitt Extremal descendant integrals on moduli spaces of curves: An inequality discovered and proved in collaboration with AI. arXiv.2512.14575 [math.AG] (2025)."},{"key":"e_1_3_2_68_2","unstructured":"V. Jain C. Mizgerd Equality in Fill\u2019s spectral gap problem. arXiv.2604.03937 [math.CO] (2026)."},{"key":"e_1_3_2_69_2","unstructured":"M. Putterman M. Sawhney G. Valiant On infinite sets with no 3 on a line. arXiv.2602.21275 [math.CO] (2026)."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1112\/jlms.12987"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1957.7.961"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1002\/jgt.3190010306"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1016\/0001-8708(78)90045-2"},{"key":"e_1_3_2_74_2","unstructured":"H. Shugart J. M. Altschuler Negative stepsizes make gradient-descent-ascent converge. arXiv.2505.01423 [math.OC] (2025)."},{"key":"e_1_3_2_75_2","volume-title":"International Conference on Learning Representations","author":"Madry A.","year":"2018","unstructured":"A. Madry, A. Makelov, L. Schmidt, D. Tsipras, A. Vladu, Towards Deep Learning Models Resistant to Adversarial Attacks, in International Conference on Learning Representations (2018)."},{"key":"e_1_3_2_76_2","volume-title":"International Conference on Machine Learning","author":"Du S. S.","year":"2017","unstructured":"S. S. Du, J. Chen, L. Li, L. Xiao, D. Zhou, Stochastic variance reduction methods for policy evaluation, in International Conference on Machine Learning (2017)."},{"key":"e_1_3_2_77_2","volume-title":"Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics","author":"Alvarez-Melis D.","year":"2018","unstructured":"D. Alvarez-Melis, T. Jaakkola, S. Jegelka, Structured Optimal Transport, in Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (2018)."},{"key":"e_1_3_2_78_2","volume-title":"International Conference on Machine Learning","author":"Agarwal A.","year":"2018","unstructured":"A. Agarwal, A. Beygelzimer, M. Dudik, J. Langford, H. Wallach, A reductions approach to fair classification, in International Conference on Machine Learning (2018)."},{"key":"e_1_3_2_79_2","volume-title":"International Conference on Learning Representations","author":"Daskalakis C.","year":"2018","unstructured":"C. Daskalakis, A. Ilyas, V. Syrgkanis, H. Zeng, Training GANs with Optimism, in International Conference on Learning Representations (2018)."},{"key":"e_1_3_2_80_2","unstructured":"H. Shugart J. M. Altschuler Negative stepsizes make gradient-descent-ascent converge. arXiv preprint arXiv:2505.01423 (2025)."},{"key":"e_1_3_2_81_2","first-page":"747","article-title":"The extragradient method for finding saddle points and other problems","volume":"12","author":"Korpelevich G. M.","year":"1976","unstructured":"G. M. Korpelevich, The extragradient method for finding saddle points and other problems. \u042d\u043a\u043e\u043d. \u0438 \u043c\u0430\u0442. \u043c\u0435\u0442\u043e\u0434\u044b 12, 747\u2013756 (1976).","journal-title":"\u042d\u043a\u043e\u043d. \u0438 \u043c\u0430\u0442. \u043c\u0435\u0442\u043e\u0434\u044b"},{"key":"e_1_3_2_82_2","first-page":"\u2022\u2022\u2022","article-title":"On the convergence of single-call stochastic extra-gradient methods","volume":"32","author":"Hsieh Y.-G.","year":"2019","unstructured":"Y.-G. Hsieh, F. Iutzeler, J. Malick, P. Mertikopoulos, On the convergence of single-call stochastic extra-gradient methods. Adv. Neural Inf. Process. Syst. 32, \u2022\u2022\u2022 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_83_2","unstructured":"Y. Cai A. Oikonomou W. Zheng Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities. arXiv.2204.09228 [math.OC] (2022)."},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01141092"},{"key":"e_1_3_2_85_2","unstructured":"N. Golowich S. Pattathil C. Daskalakis Tight last-iterate convergence rates for no-regret learning in multi-player games in Advances in Neural Information Processing Systems (2020)."},{"key":"e_1_3_2_86_2","volume-title":"International Conference on Learning Representations","author":"Cai Y.","year":"2023","unstructured":"Y. Cai, W. Zheng, Accelerated Single-Call Methods for Constrained Min-Max Optimization, in International Conference on Learning Representations (2023)."},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1589"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1967-11864-0"},{"key":"e_1_3_2_89_2","first-page":"1428","volume-title":"Conference on Learning Theory","author":"Diakonikolas J.","year":"2020","unstructured":"J. Diakonikolas, Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalities, in Conference on Learning Theory (2020), pp. 1428\u20131451."},{"key":"e_1_3_2_90_2","volume-title":"International Conference on Machine Learning","author":"Yoon T.","year":"2021","unstructured":"T. Yoon, E. K. Ryu, Accelerated algorithms for smooth convex-concave minimax problems with O1\/k2. rate on squared gradient norm, in International Conference on Machine Learning (2021)."},{"key":"e_1_3_2_91_2","article-title":"Fast extragradient methods for smooth structured nonconvex-nonconcave minimax problems","author":"Lee S.","year":"2021","unstructured":"S. Lee, D. Kim, Fast extragradient methods for smooth structured nonconvex-nonconcave minimax problems. Adv. Neural Inf. Process. Syst. (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_92_2","unstructured":"S. Lee D. Kim Semi-Anchored Gradient Methods for Nonconvex-Nonconcave Minimax Problems (2024) https:\/\/openreview.net\/forum?id=rmLTwKGiSP."},{"key":"e_1_3_2_93_2","first-page":"1","article-title":"Near-Optimal Algorithms for Makinghe Gradient Small in Stochastic Minimax Optimization","volume":"25","author":"Chen L.","year":"2024","unstructured":"L. Chen, L. Luo, Near-Optimal Algorithms for Makinghe Gradient Small in Stochastic Minimax Optimization. J. Mach. Learn. Res. 25, 1\u201344 (2024).","journal-title":"J. Mach. Learn. Res."}],"container-title":["Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/science.aej2213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:01:19Z","timestamp":1791482479000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/science.aej2213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":92,"journal-issue":{"issue":"6820","published-print":{"date-parts":[[2026,10,8]]}},"alternative-id":["10.1126\/science.aej2213"],"URL":"https:\/\/doi.org\/10.1126\/science.aej2213","relation":{},"ISSN":["0036-8075","1095-9203"],"issn-type":[{"value":"0036-8075","type":"print"},{"value":"1095-9203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]},"assertion":[{"value":"2026-05-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}