{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:07:04Z","timestamp":1776064024859,"version":"3.50.1"},"reference-count":91,"publisher":"Springer Science and Business Media LLC","issue":"7995","license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2024,1,18]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements<jats:sup>1,2<\/jats:sup>. This hinders the use of current large models in scientific discovery. Here we introduce FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator. We demonstrate the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches<jats:sup>3<\/jats:sup>. Applying FunSearch to a central problem in extremal combinatorics\u2014the cap set problem\u2014we discover new constructions of large cap sets going beyond the best-known ones, both in finite dimensional and asymptotic cases. This shows that it is possible to make discoveries for established open problems using LLMs. We showcase the generality of FunSearch by applying it to an algorithmic problem, online bin packing, finding new heuristics that improve on widely used baselines. In contrast to most computer search approaches, FunSearch searches for programs that describe how to solve a problem, rather than what the solution is. Beyond being an effective and scalable strategy, discovered programs tend to be more interpretable than raw solutions, enabling feedback loops between domain experts and FunSearch, and the deployment of such programs in real-world applications.<\/jats:p>","DOI":"10.1038\/s41586-023-06924-6","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T17:02:21Z","timestamp":1702573341000},"page":"468-475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":291,"title":["Mathematical discoveries from program search with large language models"],"prefix":"10.1038","volume":"625","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3604-3590","authenticated-orcid":false,"given":"Bernardino","family":"Romera-Paredes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8470-8203","authenticated-orcid":false,"given":"Mohammadamin","family":"Barekatain","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Novikov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5552-9855","authenticated-orcid":false,"given":"Matej","family":"Balog","sequence":"additional","affiliation":[]},{"given":"M. Pawan","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Emilien","family":"Dupont","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2200-901X","authenticated-orcid":false,"given":"Francisco J. R.","family":"Ruiz","sequence":"additional","affiliation":[]},{"given":"Jordan S.","family":"Ellenberg","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4976-4267","authenticated-orcid":false,"given":"Pengming","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Omar","family":"Fawzi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7466-7997","authenticated-orcid":false,"given":"Pushmeet","family":"Kohli","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7341-1917","authenticated-orcid":false,"given":"Alhussein","family":"Fawzi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,14]]},"reference":[{"key":"6924_CR1","unstructured":"Bang, Y. et al. A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. Preprint at https:\/\/arxiv.org\/abs\/2302.04023 (2023)."},{"key":"6924_CR2","doi-asserted-by":"crossref","unstructured":"Borji, A. A. categorical archive of ChatGPT failures. Preprint at https:\/\/arxiv.org\/abs\/2302.03494 (2023).","DOI":"10.21203\/rs.3.rs-2895792\/v1"},{"key":"6924_CR3","doi-asserted-by":"crossref","unstructured":"Lehman, J. et al. in Handbook of Evolutionary Machine Learning (eds Banzhaf, W. et al.) 331\u2013366 (Springer, 2023).","DOI":"10.1007\/978-981-99-3814-8_11"},{"key":"6924_CR4","unstructured":"Chen, M. et al. Evaluating large language models trained on code. Preprint at https:\/\/arxiv.org\/abs\/2107.03374 (2021)."},{"key":"6924_CR5","unstructured":"Austin, J. et al. Program synthesis with large language models. Preprint at https:\/\/arxiv.org\/abs\/2108.07732 (2021)."},{"key":"6924_CR6","unstructured":"Li, R. et al. StarCoder: may the source be with you! Preprint at https:\/\/arxiv.org\/abs\/2305.06161 (2023)."},{"key":"6924_CR7","unstructured":"Fried, D. et al. Incoder: a generative model for code infilling and synthesis. In Proc. International Conference on Learning Representations (2022)."},{"key":"6924_CR8","unstructured":"Nijkamp, E. et al. CodeGen: an open large language model for code with multi-turn program synthesis. In Proc. International Conference on Learning Representations (2022)."},{"key":"6924_CR9","unstructured":"Chen, X., Lin, M., Sch\u00e4rli, N. & Zhou, D. Teaching large language models to self-debug. Preprint at https:\/\/arxiv.org\/abs\/2304.05128 (2023)."},{"key":"6924_CR10","doi-asserted-by":"crossref","unstructured":"Liventsev, V., Grishina, A., H\u00e4rm\u00e4, A. & Moonen, L. Fully autonomous programming with large language models. Preprint at https:\/\/arxiv.org\/abs\/2304.10423 (2023).","DOI":"10.1145\/3583131.3590481"},{"key":"6924_CR11","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1126\/science.abq1158","volume":"378","author":"Y Li","year":"2022","unstructured":"Li, Y. et al. Competition-level code generation with alphacode. Science 378, 1092\u20131097 (2022).","journal-title":"Science"},{"key":"6924_CR12","unstructured":"Zelikman, E., Huang, Q., Poesia, G., Goodman, N. D. & Haber, N. Parsel: a (de-) compositional framework for algorithmic reasoning with language models. Preprint at https:\/\/arxiv.org\/abs\/2212.10561 (2023)."},{"key":"6924_CR13","unstructured":"Madaan, A. et al. Learning performance-improving code edits. Preprint at https:\/\/arxiv.org\/abs\/2302.07867 (2023)."},{"key":"6924_CR14","unstructured":"Goldberg, D. E. Genetic Algorithms in Search, Optimization and Machine Learning (Addison-Wesley, 1989)."},{"key":"6924_CR15","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/BF00175355","volume":"4","author":"JR Koza","year":"1994","unstructured":"Koza, J. R. Genetic programming as a means for programming computers by natural selection. Stat. Comput. 4, 87\u2013112 (1994).","journal-title":"Stat. Comput."},{"key":"6924_CR16","doi-asserted-by":"crossref","unstructured":"Meyerson, E. et al. Language model crossover: variation through few-shot prompting. Preprint at https:\/\/arxiv.org\/abs\/2302.12170 (2023).","DOI":"10.1145\/3694791"},{"key":"6924_CR17","unstructured":"Chen, A., Dohan, D. M. & So, D. R. EvoPrompting: language models for code-level neural architecture search. Preprint at https:\/\/arxiv.org\/abs\/2302.14838 (2023)."},{"key":"6924_CR18","unstructured":"Zheng, M. et al. Can GPT-4 perform neural architecture search? Preprint at https:\/\/arxiv.org\/abs\/2304.10970 (2023)."},{"key":"6924_CR19","doi-asserted-by":"crossref","unstructured":"Nasir, M. U., Earle, S., Togelius, J., James, S. & Cleghorn, C. LLMatic: neural architecture search via large language models and quality-diversity optimization. Preprint at https:\/\/arxiv.org\/abs\/2306.01102 (2023).","DOI":"10.1145\/3638529.3654017"},{"key":"6924_CR20","unstructured":"Haluptzok, P., Bowers, M. & Kalai, A. T. Language models can teach themselves to program better. In International Conference on Learning Representations (2023)."},{"key":"6924_CR21","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1090\/bull\/1648","volume":"56","author":"J Grochow","year":"2019","unstructured":"Grochow, J. New applications of the polynomial method: the cap set conjecture and beyond. Bull. Am. Math. Soc. 56, 29\u201364 (2019).","journal-title":"Bull. Am. Math. Soc."},{"key":"6924_CR22","doi-asserted-by":"crossref","unstructured":"Tao, T. & Vu, V. H. Additive Combinatorics Vol. 105 (Cambridge Univ. Press, 2006).","DOI":"10.1017\/CBO9780511755149"},{"key":"6924_CR23","doi-asserted-by":"crossref","unstructured":"Beasley, J. E. OR-library: distributing test problems by electronic mail. J. Oper. Res. Soc. 41, 1069\u20131072 (1990).","DOI":"10.1038\/sj\/jors\/0411109"},{"key":"6924_CR24","doi-asserted-by":"crossref","unstructured":"Casti\u00f1eiras, I., De Cauwer, M. & O\u2019Sullivan, B. Weibull-based benchmarks for bin packing. In Proc. International Conference on Principles and Practice of Constraint Programming 207\u2013222 (Springer, 2012).","DOI":"10.1007\/978-3-642-33558-7_17"},{"key":"6924_CR25","unstructured":"Anil, R. et al. Palm 2 technical report. Preprint at https:\/\/arxiv.org\/abs\/2305.10403 (2023)."},{"key":"6924_CR26","unstructured":"Code models overview. Vertex AI, Google Cloud https:\/\/cloud.google.com\/vertex-ai\/docs\/generative-ai\/code\/code-models-overview (2023)."},{"key":"6924_CR27","unstructured":"Tanese, R. Distributed Genetic Algorithms for Function Optimization. PhD thesis, Univ. Michigan (1989)."},{"key":"6924_CR28","first-page":"141","volume":"10","author":"E Cant\u00fa-Paz","year":"1998","unstructured":"Cant\u00fa-Paz, E. A survey of parallel genetic algorithms. Calculateurs Paralleles, Reseaux et Systemes Repartis 10, 141\u2013171 (1998).","journal-title":"Calculateurs Paralleles, Reseaux et Systemes Repartis"},{"key":"6924_CR29","unstructured":"Tao, T. Open question: best bounds for cap sets. WordPress Blog https:\/\/terrytao.wordpress.com\/2007\/02\/23\/open-question-best-bounds-for-cap-sets\/ (2009)."},{"key":"6924_CR30","doi-asserted-by":"crossref","unstructured":"Croot, E., Lev, V. F. & Pach, P. P. Progression-free sets in are exponentially small. Ann. Math. 185, 331\u2013337 (2017).","DOI":"10.4007\/annals.2017.185.1.7"},{"key":"6924_CR31","doi-asserted-by":"crossref","unstructured":"Ellenberg, J. S., Gijswijt, D. On large subsets of $${F}_{q}^{n}$$ with no three-term arithmetic progression. Ann. Math. 185, 339\u2013343 (2017).","DOI":"10.4007\/annals.2017.185.1.8"},{"key":"6924_CR32","doi-asserted-by":"crossref","unstructured":"Naslund, E. & Sawin, W. Upper bounds for sunflower-free sets. Forum Math. Sigma 5, e15 (2017).","DOI":"10.1017\/fms.2017.12"},{"key":"6924_CR33","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1023\/A:1011216716700","volume":"23","author":"Y Edel","year":"2001","unstructured":"Edel, Y. & Bierbrauer, J. Large caps in small spaces. Des. Codes Cryptogr. 23, 197\u2013212 (2001).","journal-title":"Des. Codes Cryptogr."},{"key":"6924_CR34","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1027365901231","volume":"31","author":"Y Edel","year":"2004","unstructured":"Edel, Y. Extensions of generalized product caps. Des. Codes Cryptogr. 31, 5\u201314 (2004).","journal-title":"Des. Codes Cryptogr."},{"key":"6924_CR35","first-page":"378","volume":"54","author":"R Hill","year":"1973","unstructured":"Hill, R. On the largest size of cap in S5,3. Rend Lincei. Sci. Fis. Mat. Nat. 54, 378\u2013384 (1973).","journal-title":"Rend Lincei. Sci. Fis. Mat. Nat."},{"key":"6924_CR36","doi-asserted-by":"crossref","unstructured":"Cameron, P. J. & Van Lint, J. H. Designs, Graphs, Codes and Their Links Vol. 3 (Cambridge Univ. Press, 1991).","DOI":"10.1017\/CBO9780511623714"},{"key":"6924_CR37","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/BF01388452","volume":"4","author":"AR Calderbank","year":"1994","unstructured":"Calderbank, A. R. & Fishburn, P. C. Maximal three-independent subsets of {0,\u20091,\u20092} n. Des. Codes Cryptogr. 4, 203\u2013211 (1994).","journal-title":"Des. Codes Cryptogr."},{"key":"6924_CR38","doi-asserted-by":"publisher","unstructured":"Tyrrell, F. New lower bounds for cap sets. Discrete Analysis https:\/\/doi.org\/10.19086\/da.91076 (2023).","DOI":"10.19086\/da.91076"},{"key":"6924_CR39","doi-asserted-by":"crossref","unstructured":"Coffman, E. G., Garey, M. R. & Johnson, D. S. in Algorithm Design for Computer System Design (eds Ausiello, G. et al.) 49\u2013106 (Springer, 1984).","DOI":"10.1007\/978-3-7091-4338-4_3"},{"key":"6924_CR40","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1145\/3828.3833","volume":"32","author":"CC Lee","year":"1985","unstructured":"Lee, C. C. & Lee, D. T. A simple on-line bin-packing algorithm. J. ACM 32, 562\u2013572 (1985).","journal-title":"J. ACM"},{"key":"6924_CR41","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/0196-6774(89)90031-X","volume":"10","author":"P Ramanan","year":"1989","unstructured":"Ramanan, P., Brown, D. J., Lee, C.-C. & Lee, D.-T. On-line bin packing in linear time. J. Algorithm. 10, 305\u2013326 (1989).","journal-title":"J. Algorithm."},{"key":"6924_CR42","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1145\/585265.585269","volume":"49","author":"SS Seiden","year":"2002","unstructured":"Seiden, S. S. On the online bin packing problem. J. ACM 49, 640\u2013671 (2002).","journal-title":"J. ACM"},{"key":"6924_CR43","doi-asserted-by":"crossref","unstructured":"Balogh, J., B\u00e9k\u00e9si, J., D\u00f3sa, G., Sgall, J. & Stee, R. V. The optimal absolute ratio for online bin packing. In Proc. Twenty-Sixth Annual ACM-SIAM Symposium on Discrete Algorithms, SIAM (ed. Chekuri, C.) 1425\u20131438 (SIAM, 2014).","DOI":"10.1137\/1.9781611973730.94"},{"key":"6924_CR44","unstructured":"Balogh, J., B\u00e9k\u00e9si, J., D\u00f3sa, G., Epstein, L. & Levin, A. A new and improved algorithm for online bin packing. In Proc. 26th Annual European Symposium on Algorithms (ESA 2018) 5:1\u20135:14 (Schloss Dagstuhl\u2013Leibniz-Zentrum fuer Informatik, 2018)."},{"key":"6924_CR45","doi-asserted-by":"crossref","unstructured":"Coffman, E. G., Csirik, J., Galambos, G., Martello, S. & Vigo, D. in Handbook of Combinatorial Optimization (eds Pardalos, P. M. et al.) 455\u2013531 (Springer, 2013).","DOI":"10.1007\/978-1-4419-7997-1_35"},{"key":"6924_CR46","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/0166-218X(90)90094-S","volume":"28","author":"S Martello","year":"1990","unstructured":"Martello, S. & Toth, P. Lower bounds and reduction procedures for the bin packing problem. Discrete Appl. Math. 28, 59\u201370 (1990).","journal-title":"Discrete Appl. Math."},{"key":"6924_CR47","doi-asserted-by":"crossref","unstructured":"Angelopoulos, S., Kamali, S. & Shadkami, K. Online bin packing with predictions. J. Artif. Intell. Res. 36, 4574\u20134580 (2022).","DOI":"10.24963\/ijcai.2022\/635"},{"key":"6924_CR48","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1145\/321356.321363","volume":"13","author":"GJ Chaitin","year":"1966","unstructured":"Chaitin, G. J. On the length of programs for computing finite binary sequences. J. ACM 13, 547\u2013569 (1966).","journal-title":"J. ACM"},{"key":"6924_CR49","doi-asserted-by":"crossref","unstructured":"Li, M. et al. An Introduction to Kolmogorov Complexity and its Applications Vol. 3 (Springer, 2008).","DOI":"10.1007\/978-0-387-49820-1"},{"key":"6924_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0019-9958(64)90223-2","volume":"7","author":"RJ Solomonoff","year":"1964","unstructured":"Solomonoff, R. J. A formal theory of inductive inference. Part I. Inf. Control 7, 1\u201322 (1964).","journal-title":"Inf. Control"},{"key":"6924_CR51","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s10710-010-9113-2","volume":"11","author":"M O\u2019Neill","year":"2010","unstructured":"O\u2019Neill, M., Vanneschi, L., Gustafson, S. & Banzhaf, W. Open issues in genetic programming. Genet. Program. Evolvable Mach. 11, 339\u2013363 (2010).","journal-title":"Genet. Program. Evolvable Mach."},{"key":"6924_CR52","unstructured":"Polu, S. & Sutskever, I. Generative language modeling for automated theorem proving. Preprint at https:\/\/arxiv.org\/abs\/2009.03393 (2020)."},{"key":"6924_CR53","unstructured":"Polu, S. et al. Formal mathematics statement curriculum learning. In International Conference on Learning Representations (2023)."},{"key":"6924_CR54","first-page":"8360","volume":"35","author":"AQ Jiang","year":"2022","unstructured":"Jiang, A. Q. et al. THOR: wielding hammers to integrate language models and automated theorem provers. Adv. Neural Info. Process. Syst. 35, 8360\u20138373 (2022).","journal-title":"Adv. Neural Info. Process. Syst."},{"key":"6924_CR55","doi-asserted-by":"crossref","unstructured":"Mouret, J.-B. & Doncieux, S. Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In Proc. 2009 IEEE Congress on Evolutionary Computation 1161\u20131168 (IEEE, 2009).","DOI":"10.1109\/CEC.2009.4983077"},{"key":"6924_CR56","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frobt.2016.00040","volume":"3","author":"JK Pugh","year":"2016","unstructured":"Pugh, J. K., Soros, L. B. & Stanley, K. O. Quality diversity: a new frontier for evolutionary computation. Front. Robotics AI 3, 40 (2016).","journal-title":"Front. Robotics AI"},{"key":"6924_CR57","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TEVC.2014.2362729","volume":"19","author":"T Helmuth","year":"2015","unstructured":"Helmuth, T., Spector, L. & Matheson, J. Solving uncompromising problems with lexicase selection. IEEE Trans. Evol. Comput. 19, 630\u2013643 (2015).","journal-title":"IEEE Trans. Evol. Comput."},{"key":"6924_CR58","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/TEVC.2005.863127","volume":"10","author":"M Hutter","year":"2006","unstructured":"Hutter, M. & Legg, S. Fitness uniform optimization. IEEE Trans. Evol. Comput. 10, 568\u2013589 (2006).","journal-title":"IEEE Trans. Evol. Comput."},{"key":"6924_CR59","unstructured":"de la Maza, M. An analysis of selection procedures with particular attention paid to proportional and Boltzmann selection. In Proc. Fifth International Conference on Genetic Algorithms (Morgan Kaufmann, 1993)."},{"key":"6924_CR60","unstructured":"OpenAI, GPT-4 technical report. Preprint at https:\/\/arxiv.org\/abs\/2303.08774 (2023)."},{"key":"6924_CR61","unstructured":"Millidge, B. Scaffolded LLMs as natural language computers. Beren\u2019s Blog https:\/\/www.beren.io\/2023-04-11-Scaffolded-LLMs-natural-language-computers (2023)."},{"key":"6924_CR62","unstructured":"Schick, T. et al. Toolformer: language models can teach themselves to use tools. Preprint at https:\/\/arxiv.org\/abs\/2302.04761 (2023)."},{"key":"6924_CR63","doi-asserted-by":"crossref","unstructured":"Park, J. S. et al. Generative agents: interactive simulacra of human behavior. In Proc. 36th Annual ACM Symposium on User Interface Software and Technology1\u201322 (ACM, 2023).","DOI":"10.1145\/3586183.3606763"},{"key":"6924_CR64","unstructured":"Wu, J. et al. Recursively summarizing books with human feedback. Preprint at https:\/\/arxiv.org\/abs\/2109.10862 (2021)."},{"key":"6924_CR65","unstructured":"Nye, M. et al. Show your work: scratchpads for intermediate computation with language models. In Deep Learning for Code Workshop, International Conference on Learning Representations (2022)."},{"key":"6924_CR66","unstructured":"Yao, S. et al. ReAct: dynergizing reasoning and acting in language models. In Proc. International Conference on Learning Representations (2023)."},{"key":"6924_CR67","first-page":"15476","volume":"35","author":"E Zelikman","year":"2022","unstructured":"Zelikman, E., Wu, Y., Mu, J. & Goodman, N. Star: bootstrapping reasoning with reasoning. Adv. Neural Info. Process. Syst. 35, 15476\u201315488 (2022).","journal-title":"Adv. Neural Info. Process. Syst."},{"key":"6924_CR68","unstructured":"Wang, G. et al. Voyager: an open-ended embodied agent with large language models. Preprint at https:\/\/arxiv.org\/abs\/2305.16291 (2023)."},{"key":"6924_CR69","unstructured":"Yin, P. et al. Natural language to code generation in interactive data science notebooks. Preprint at https:\/\/arxiv.org\/abs\/2212.09248 (2022)."},{"key":"6924_CR70","unstructured":"Ni, A. et al. Lever: learning to verify language-to-code generation with execution. In Proc. International Conference on Machine Learning 26106\u201326128 (PMLR, 2023)."},{"key":"6924_CR71","unstructured":"Zhou, S., Alon, U., Xu, F. F., Jiang, Z. & Neubig, G. Docprompting: generating code by retrieving the docs. In Proc. International Conference on Learning Representations (2022)."},{"key":"6924_CR72","unstructured":"Banzhaf, W., Nordin, P., Keller, R. E. & Francone, F. D. Genetic Programming: An Introduction: On The Automatic Evolution of Computer Programs and its Applications (Morgan Kaufmann, 1998)."},{"key":"6924_CR73","unstructured":"Langdon, W. B. & Poli, R. Foundations of Genetic Programming (Springer Science & Business Media, 2013)."},{"key":"6924_CR74","doi-asserted-by":"publisher","first-page":"eabq0279","DOI":"10.1126\/sciadv.abq0279","volume":"8","author":"H Ma","year":"2022","unstructured":"Ma, H., Narayanaswamy, A., Riley, P. & Li, L. Evolving symbolic density functionals. Sci. Adv. 8, eabq0279 (2022).","journal-title":"Sci. Adv."},{"key":"6924_CR75","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1126\/science.1165893","volume":"324","author":"M Schmidt","year":"2009","unstructured":"Schmidt, M. & Lipson, H. Distilling free-form natural laws from experimental data. Science 324, 81\u201385 (2009).","journal-title":"Science"},{"key":"6924_CR76","unstructured":"Chen, X. et al. Symbolic discovery of optimization algorithms. Preprint at https:\/\/arxiv.org\/abs\/2302.06675 (2023)."},{"key":"6924_CR77","unstructured":"Koza, J. R. Genetic Programming II: Automatic Discovery of Reusable Programs (MIT, 1994)."},{"key":"6924_CR78","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1162\/evco.1997.5.2.123","volume":"5","author":"R Salustowicz","year":"1997","unstructured":"Salustowicz, R. & Schmidhuber, J. Probabilistic incremental program evolution. Evol. Comput. 5, 123\u2013141 (1997).","journal-title":"Evol. Comput."},{"key":"6924_CR79","unstructured":"Burke, E. et al. in Handbook of Metaheuristics (eds Glover, F. & Kochenberger, G. A.) 457\u2013474 (Springer, 2003)."},{"key":"6924_CR80","unstructured":"Ross, P. in Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques (eds Burke, E. K. & Kendall, G.) 529\u2013556 (Springer, 2005)."},{"key":"6924_CR81","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1057\/jors.2013.71","volume":"64","author":"EK Burke","year":"2013","unstructured":"Burke, E. K. et al. Hyper-heuristics: a survey of the state of the art. J. Oper. Res. Soc. 64, 1695\u20131724 (2013).","journal-title":"J. Oper. Res. Soc."},{"key":"6924_CR82","doi-asserted-by":"crossref","unstructured":"Burke, E. K., Hyde, M. R. & Kendall, G. Evolving bin packing heuristics with genetic programming. In Proc. International Conference on Parallel Problem Solving from Nature 860\u2013869 (Springer, 2006).","DOI":"10.1007\/11844297_87"},{"key":"6924_CR83","doi-asserted-by":"crossref","unstructured":"Burke, E. K., Hyde, M. R., Kendall, G. & Woodward, J. Automatic heuristic generation with genetic programming: evolving a jack-of-all-trades or a master of one. In Proc. 9th Annual Conference on Genetic and Evolutionary Computation 1559\u20131565 (ACM, 2007).","DOI":"10.1145\/1276958.1277273"},{"key":"6924_CR84","doi-asserted-by":"crossref","unstructured":"Burke, E. K., Hyde, M. R. & Kendall, G. Providing a memory mechanism to enhance the evolutionary design of heuristics. In Proc. IEEE Congress on Evolutionary Computation 1\u20138 (IEEE, 2010).","DOI":"10.1109\/CEC.2010.5586388"},{"key":"6924_CR85","doi-asserted-by":"crossref","unstructured":"Burke, E. K., Hyde, M., Kendall, G. & Woodward, J. R. The scalability of evolved on line bin packing heuristics. In Proc. 2007 IEEE Congress on Evolutionary Computation 2530\u20132537 (IEEE, 2007).","DOI":"10.1109\/CEC.2007.4424789"},{"key":"6924_CR86","unstructured":"Bunel, R., Desmaison, A., Kohli, P., Torr, P. H. & Kumar, M. P. Learning to superoptimize programs. In Proc. International Conference on Learning Representations (2017)."},{"key":"6924_CR87","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1145\/2490301.2451150","volume":"41","author":"E Schkufza","year":"2013","unstructured":"Schkufza, E., Sharma, R. & Aiken, A. Stochastic superoptimization. ACM SIGARCH Comp. Archit. News 41, 305\u2013316 (2013).","journal-title":"ACM SIGARCH Comp. Archit. News"},{"key":"6924_CR88","unstructured":"Shypula, A. et al. Learning to superoptimize real-world programs. In Proc. Deep Learning for Code Workshop (ICLR 2022 Workshop) (2022)."},{"key":"6924_CR89","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41586-022-05172-4","volume":"610","author":"A Fawzi","year":"2022","unstructured":"Fawzi, A. et al. Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610, 47\u201353 (2022).","journal-title":"Nature"},{"key":"6924_CR90","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s41586-023-06004-9","volume":"618","author":"DJ Mankowitz","year":"2023","unstructured":"Mankowitz, D. J. et al. Faster sorting algorithms discovered using deep reinforcement learning. Nature 618, 257\u2013263 (2023).","journal-title":"Nature"},{"key":"6924_CR91","doi-asserted-by":"crossref","unstructured":"Yang, F. et al. Launchpad: a programming model for distributed machine learning research. Preprint at https:\/\/arxiv.org\/abs\/2106.04516 (2021).","DOI":"10.1155\/2021\/6593438"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-023-06924-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-023-06924-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-023-06924-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T01:25:41Z","timestamp":1730856341000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-023-06924-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"references-count":91,"journal-issue":{"issue":"7995","published-print":{"date-parts":[[2024,1,18]]}},"alternative-id":["6924"],"URL":"https:\/\/doi.org\/10.1038\/s41586-023-06924-6","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,14]]},"assertion":[{"value":"12 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors of the paper are planning to file a patent application relating to subject matter contained in this paper in the name of Google DeepMind.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}