Mathematical discoveries from program search with large language models

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 1...

Full description

Saved in:
Bibliographic Details
Published inNature (London) Vol. 625; no. 7995; pp. 468 - 475
Main Authors Romera-Paredes, Bernardino, Barekatain, Mohammadamin, Novikov, Alexander, Balog, Matej, Kumar, M. Pawan, Dupont, Emilien, Ruiz, Francisco J. R., Ellenberg, Jordan S., Wang, Pengming, Fawzi, Omar, Kohli, Pushmeet, Fawzi, Alhussein
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 18.01.2024
Nature Publishing Group
Subjects
639/705/1045
639/705/117
Algorithms
Applications programs
Artificial Intelligence
Combinatorial analysis
Combinatorics
Computer Science
Design specifications
Feedback loops
Function space
Humanities and Social Sciences
Language
Large language models
Mathematical models
multidisciplinary
Natural language (computers)
Neural networks
Science
Science (multidisciplinary)
Subject specialists
Task complexity
Online AccessGet full text

Cover

Abstract 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 1 , 2 . 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 3 . Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we 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. FunSearch makes discoveries in established open problems using large language models by searching for programs describing how to solve a problem, rather than what the solution is.
AbstractList 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 1 , 2 . 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 3 . Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we 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. FunSearch makes discoveries in established open problems using large language models by searching for programs describing how to solve a problem, rather than what the solution is.
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 [1,2]. 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 pre-trained 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 [3]. Applying FunSearch to a central problem in extremal combinatorics - the cap set problem - we discover new constructions of large cap sets going beyond the best known ones, both in finite dimensional and asymptotic cases. This represents the first discoveries made 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 upon 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.
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 statements1,2. 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 approaches3. Applying FunSearch to a central problem in extremal combinatorics-the cap set problem-we 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.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 statements1,2. 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 approaches3. Applying FunSearch to a central problem in extremal combinatorics-the cap set problem-we 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.
Abstract 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. 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. Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we 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.
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 1,2 . 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 3 . Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we 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.
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 statements1,2. 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 approaches3. Applying FunSearch to a central problem in extremal combinatorics-the cap set problem-we 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.
Author Balog, Matej
Kumar, M. Pawan
Dupont, Emilien
Ruiz, Francisco J. R.
Fawzi, Alhussein
Ellenberg, Jordan S.
Wang, Pengming
Fawzi, Omar
Barekatain, Mohammadamin
Romera-Paredes, Bernardino
Kohli, Pushmeet
Novikov, Alexander
Author_xml – sequence: 1
  givenname: Bernardino
  orcidid: 0000-0003-3604-3590
  surname: Romera-Paredes
  fullname: Romera-Paredes, Bernardino
  email: brp@google.com
  organization: Google DeepMind
– sequence: 2
  givenname: Mohammadamin
  orcidid: 0000-0002-8470-8203
  surname: Barekatain
  fullname: Barekatain, Mohammadamin
  organization: Google DeepMind
– sequence: 3
  givenname: Alexander
  surname: Novikov
  fullname: Novikov, Alexander
  organization: Google DeepMind
– sequence: 4
  givenname: Matej
  orcidid: 0000-0002-5552-9855
  surname: Balog
  fullname: Balog, Matej
  organization: Google DeepMind
– sequence: 5
  givenname: M. Pawan
  surname: Kumar
  fullname: Kumar, M. Pawan
  organization: Google DeepMind
– sequence: 6
  givenname: Emilien
  surname: Dupont
  fullname: Dupont, Emilien
  organization: Google DeepMind
– sequence: 7
  givenname: Francisco J. R.
  orcidid: 0000-0002-2200-901X
  surname: Ruiz
  fullname: Ruiz, Francisco J. R.
  organization: Google DeepMind
– sequence: 8
  givenname: Jordan S.
  surname: Ellenberg
  fullname: Ellenberg, Jordan S.
  organization: Department of Mathematics, University of Wisconsin-Madison
– sequence: 9
  givenname: Pengming
  orcidid: 0009-0009-4976-4267
  surname: Wang
  fullname: Wang, Pengming
  organization: Google DeepMind
– sequence: 10
  givenname: Omar
  surname: Fawzi
  fullname: Fawzi, Omar
  organization: Laboratoire de l’Informatique du Parallélisme, University of Lyon (Inria, ENS Lyon, UCBL, LIP)
– sequence: 11
  givenname: Pushmeet
  orcidid: 0000-0002-7466-7997
  surname: Kohli
  fullname: Kohli, Pushmeet
  email: pushmeet@google.com
  organization: Google DeepMind
– sequence: 12
  givenname: Alhussein
  orcidid: 0000-0001-7341-1917
  surname: Fawzi
  fullname: Fawzi, Alhussein
  email: afawzi@google.com
  organization: Google DeepMind
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38096900$$D View this record in MEDLINE/PubMed
https://hal.science/hal-04682926$$DView record in HAL
BookMark eNp9kUFv1DAQhS1URLelf4ADisQFDoGxndjOCVUVbZG26gXOluMdJ6mSeLGTrfj3eJuWwh56sS37e288807I0ehHJOQdhc8UuPoSC1oqkQPjOYiKFbl4RVa0kCIvhJJHZAXAVA6Ki2NyEuMdAJRUFm_IMVdQiQpgRa5uzNTiYKbOmj7bdNH6HYYOY-aCH7Jt8E0wQxbRBNtm993UZr0JDaZ1bGaTDoPfYB_fktfO9BHPHvdT8vPy24-L63x9e_X94nyd2xKqKa-lFJQ7MGCYcooZsBKQ12itdKaURU0NN3WJlircgMTUjkNKnZMVdaXjp-Tr4rud6wE3FscpmF5vQzeY8Ft70-n_X8au1Y3faQqyKmhRJodPi0N7oLs-X-v9HaTpsYqJHU3sx8dqwf-aMU56SBPCPjWPfo6aVcCqsoSCJ_TDAXrn5zCmWSSKSs4ZYypR7__9_t_6T4EkQC2ADT7GgE7bbkrp-H03XZ_a0Pvs9ZK9Ttnrh-y1SFJ2IH1yf1HEF1FM8NhgeP72C6o_JO7BLg
CitedBy_id crossref_primary_10_1016_j_xcrp_2024_101844
crossref_primary_10_1016_j_swevo_2024_101780
crossref_primary_10_1038_s41562_024_01991_9
crossref_primary_10_1145_3678165
crossref_primary_10_1016_j_rcim_2024_102883
crossref_primary_10_1063_5_0224297
crossref_primary_10_1021_acs_chemrestox_4c00134
crossref_primary_10_1016_j_future_2024_107481
crossref_primary_10_17726_philIT_2024_1_3
crossref_primary_10_1038_d41586_023_03998_0
crossref_primary_10_1039_D4DD00074A
crossref_primary_10_1007_s10479_024_06127_w
crossref_primary_10_2478_jdis_2024_0011
crossref_primary_10_1016_j_jsmc_2024_10_001
crossref_primary_10_2139_ssrn_4761694
crossref_primary_10_1088_2632_2153_ad743e
crossref_primary_10_1038_s41467_025_57427_z
crossref_primary_10_3390_app15042241
crossref_primary_10_1016_j_isci_2024_109550
crossref_primary_10_1109_TCYB_2024_3412997
crossref_primary_10_1016_j_procs_2024_11_094
crossref_primary_10_1038_s43588_024_00593_9
crossref_primary_10_1016_j_disc_2024_114334
crossref_primary_10_1007_s11390_024_5036_x
crossref_primary_10_1109_TBDATA_2024_3423677
crossref_primary_10_1007_s41965_024_00172_x
crossref_primary_10_1038_s42254_024_00740_1
crossref_primary_10_1007_s10998_024_00617_x
crossref_primary_10_1016_j_mattod_2024_08_028
crossref_primary_10_1126_sciadv_adr4173
crossref_primary_10_1145_3694791
crossref_primary_10_3390_sym16101388
crossref_primary_10_1021_acs_jcim_3c01726
crossref_primary_10_17726_philIT_2024_1_6
crossref_primary_10_1145_3696412
crossref_primary_10_4196_kjpp_2024_28_5_393
crossref_primary_10_1007_s10515_024_00436_x
crossref_primary_10_1007_s11704_024_40490_y
crossref_primary_10_1056_AIoa2400555
crossref_primary_10_34133_research_0442
crossref_primary_10_1063_5_0247759
crossref_primary_10_1515_revce_2024_0060
crossref_primary_10_1016_j_infoandorg_2025_100560
crossref_primary_10_1016_j_swevo_2024_101741
crossref_primary_10_1142_S201032472440006X
Cites_doi 10.1145/3583131.3590481
10.1038/s41586-023-06004-9
10.1109/CEC.2010.5586388
10.1145/585265.585269
10.1145/321356.321363
10.1126/science.abq1158
10.24963/ijcai.2022/635
10.1017/CBO9780511755149
10.1007/978-3-7091-4338-4_3
10.1007/BF01388452
10.1126/science.1165893
10.1090/bull/1648
10.1126/sciadv.abq0279
10.1007/978-1-4419-7997-1_35
10.1162/evco.1997.5.2.123
10.1038/s41586-022-05172-4
10.1145/2490301.2451150
10.1145/3828.3833
10.1016/0196-6774(89)90031-X
10.1155/2021/6593438
10.1023/A:1011216716700
10.1007/978-0-387-49820-1
10.1145/3638529.3654017
10.1007/978-981-99-3814-8_11
10.1007/BF00175355
10.21203/rs.3.rs-2895792/v1
10.1145/3694791
10.1007/978-3-642-33558-7_17
10.19086/da.91076
10.4007/annals.2017.185.1.7
10.1016/0166-218X(90)90094-S
10.1109/TEVC.2014.2362729
10.1038/sj/jors/0411109
10.1017/fms.2017.12
10.1016/S0019-9958(64)90223-2
10.1023/A:1027365901231
10.1137/1.9781611973730.94
10.1109/CEC.2009.4983077
10.1007/11844297_87
10.1007/s10710-010-9113-2
10.1109/TEVC.2005.863127
10.1109/CEC.2007.4424789
10.1145/3586183.3606763
10.3389/frobt.2016.00040
10.1057/jors.2013.71
10.1145/1276958.1277273
10.4007/annals.2017.185.1.8
10.1017/CBO9780511623714
ContentType Journal Article
Copyright The Author(s) 2023
2023. The Author(s), under exclusive licence to Springer Nature Limited.
Copyright Nature Publishing Group Jan 18, 2024
2023. The Author(s).
Attribution
Copyright_xml – notice: The Author(s) 2023
– notice: 2023. The Author(s), under exclusive licence to Springer Nature Limited.
– notice: Copyright Nature Publishing Group Jan 18, 2024
– notice: 2023. The Author(s).
– notice: Attribution
DBID C6C
AAYXX
CITATION
NPM
3V.
7QG
7QL
7QP
7QR
7RV
7SN
7SS
7ST
7T5
7TG
7TK
7TM
7TO
7U9
7X2
7X7
7XB
88A
88E
88G
88I
8AF
8AO
8C1
8FD
8FE
8FG
8FH
8FI
8FJ
8FK
8G5
ABJCF
ABUWG
AEUYN
AFKRA
ARAPS
ATCPS
AZQEC
BBNVY
BEC
BENPR
BGLVJ
BHPHI
BKSAR
C1K
CCPQU
D1I
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
GUQSH
H94
HCIFZ
K9.
KB.
KB0
KL.
L6V
LK8
M0K
M0S
M1P
M2M
M2O
M2P
M7N
M7P
M7S
MBDVC
NAPCQ
P5Z
P62
P64
PATMY
PCBAR
PDBOC
PHGZM
PHGZT
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PSYQQ
PTHSS
PYCSY
Q9U
R05
RC3
S0X
SOI
7X8
1XC
VOOES
5PM
DOI 10.1038/s41586-023-06924-6
DatabaseName Springer Nature OA Free Journals
CrossRef
PubMed
ProQuest Central (Corporate)
Animal Behavior Abstracts
Bacteriology Abstracts (Microbiology B)
Calcium & Calcified Tissue Abstracts
Chemoreception Abstracts
Nursing & Allied Health Database
Ecology Abstracts
Entomology Abstracts (Full archive)
Environment Abstracts
Immunology Abstracts
Meteorological & Geoastrophysical Abstracts
Neurosciences Abstracts
Nucleic Acids Abstracts
Oncogenes and Growth Factors Abstracts
Virology and AIDS Abstracts
Agricultural Science Collection
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Biology Database (Alumni Edition)
Medical Database (Alumni Edition)
Psychology Database (Alumni)
Science Database (Alumni Edition)
STEM Database
ProQuest Pharma Collection
Public Health Database
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Natural Science Collection
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Research Library
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest One Sustainability
ProQuest Central UK/Ireland
Advanced Technologies & Aerospace Collection
Agricultural & Environmental Science Collection
ProQuest Central Essentials
Biological Science Collection
eLibrary
ProQuest Central
Technology Collection
ProQuest Natural Science Collection (Hollins)
ProQuest Earth, Atmospheric & Aquatic Science Collection
Environmental Sciences and Pollution Management
ProQuest One Community College
ProQuest Materials Science Collection
ProQuest Central
Engineering Research Database
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
ProQuest Research Library
AIDS and Cancer Research Abstracts
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
Materials Science Database
Nursing & Allied Health Database (Alumni Edition)
Meteorological & Geoastrophysical Abstracts - Academic
ProQuest Engineering Collection
Biological Sciences
Agricultural Science Database
ProQuest Health & Medical Collection
PML(ProQuest Medical Library)
Psychology Database
Research Library
Science Database
Algology Mycology and Protozoology Abstracts (Microbiology C)
Biological Science Database
Engineering Database
Research Library (Corporate)
Nursing & Allied Health Premium
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Biotechnology and BioEngineering Abstracts
Environmental Science Database
Earth, Atmospheric & Aquatic Science Database
Materials Science Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest One Psychology
Engineering Collection
Environmental Science Collection
ProQuest Central Basic
University of Michigan
Genetics Abstracts
SIRS Editorial
Environment Abstracts
MEDLINE - Academic
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
Agricultural Science Database
ProQuest One Psychology
Research Library Prep
ProQuest Central Student
Oncogenes and Growth Factors Abstracts
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
Nucleic Acids Abstracts
elibrary
ProQuest AP Science
SciTech Premium Collection
Environmental Sciences and Pollution Management
ProQuest One Applied & Life Sciences
ProQuest One Sustainability
Health Research Premium Collection
Meteorological & Geoastrophysical Abstracts
Natural Science Collection
Health & Medical Research Collection
Biological Science Collection
Chemoreception Abstracts
ProQuest Central (New)
ProQuest Medical Library (Alumni)
Engineering Collection
Advanced Technologies & Aerospace Collection
Engineering Database
Virology and AIDS Abstracts
ProQuest Science Journals (Alumni Edition)
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
Earth, Atmospheric & Aquatic Science Database
Agricultural Science Collection
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
Biological Science Database
Ecology Abstracts
Neurosciences Abstracts
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
Environmental Science Collection
Entomology Abstracts
Nursing & Allied Health Premium
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
Environmental Science Database
ProQuest Nursing & Allied Health Source (Alumni)
Engineering Research Database
ProQuest One Academic
Calcium & Calcified Tissue Abstracts
Meteorological & Geoastrophysical Abstracts - Academic
ProQuest One Academic (New)
University of Michigan
Technology Collection
Technology Research Database
ProQuest One Academic Middle East (New)
SIRS Editorial
Materials Science Collection
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
Research Library (Alumni Edition)
ProQuest Natural Science Collection
ProQuest Pharma Collection
ProQuest Biology Journals (Alumni Edition)
ProQuest Central
Earth, Atmospheric & Aquatic Science Collection
ProQuest Health & Medical Research Collection
Genetics Abstracts
ProQuest Engineering Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Bacteriology Abstracts (Microbiology B)
Algology Mycology and Protozoology Abstracts (Microbiology C)
Agricultural & Environmental Science Collection
AIDS and Cancer Research Abstracts
Materials Science Database
ProQuest Research Library
ProQuest Materials Science Collection
ProQuest Public Health
ProQuest Central Basic
ProQuest Science Journals
ProQuest Nursing & Allied Health Source
ProQuest Psychology Journals (Alumni)
ProQuest SciTech Collection
Advanced Technologies & Aerospace Database
ProQuest Medical Library
ProQuest Psychology Journals
Animal Behavior Abstracts
Materials Science & Engineering Collection
Immunology Abstracts
Environment Abstracts
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
PubMed

MEDLINE - Academic

CrossRef
Agricultural Science Database
Database_xml – sequence: 1
  dbid: C6C
  name: Springer Nature OA Free Journals
  url: http://www.springeropen.com/
  sourceTypes: Publisher
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Sciences (General)
Physics
Computer Science
EISSN 1476-4687
EndPage 475
ExternalDocumentID PMC10794145
oai_HAL_hal_04682926v1
38096900
10_1038_s41586_023_06924_6
Genre Journal Article
GroupedDBID ---
--Z
-DZ
-ET
-~X
.55
.CO
.XZ
07C
0R~
123
186
1OL
1VR
29M
2KS
2XV
39C
41X
53G
5RE
6TJ
70F
7RV
7X2
7X7
7XC
85S
88E
88I
8AF
8AO
8C1
8CJ
8FE
8FG
8FH
8FI
8FJ
8G5
8R4
8R5
8WZ
97F
97L
A6W
A7Z
AAEEF
AAHBH
AAHTB
AAIKC
AAKAB
AAMNW
AASDW
AAYEP
AAYZH
AAZLF
ABDQB
ABFSI
ABIVO
ABJCF
ABJNI
ABLJU
ABOCM
ABPEJ
ABPPZ
ABUWG
ABWJO
ABZEH
ACBEA
ACBWK
ACGFO
ACGFS
ACGOD
ACIWK
ACKOT
ACMJI
ACNCT
ACPRK
ACWUS
ADBBV
ADFRT
ADUKH
AENEX
AEUYN
AFBBN
AFFNX
AFKRA
AFLOW
AFRAH
AFSHS
AGAYW
AGHSJ
AGHTU
AGOIJ
AGSOS
AHMBA
AHSBF
AIDUJ
ALFFA
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AMTXH
ARAPS
ARMCB
ASPBG
ATCPS
ATWCN
AVWKF
AXYYD
AZFZN
AZQEC
BBNVY
BCU
BEC
BENPR
BGLVJ
BHPHI
BIN
BKEYQ
BKKNO
BKSAR
BPHCQ
BVXVI
C6C
CCPQU
CJ0
CS3
D1I
D1J
D1K
DU5
DWQXO
E.-
E.L
EAP
EBS
EE.
EMH
EPS
EX3
EXGXG
F5P
FAC
FEDTE
FQGFK
FSGXE
FYUFA
GNUQQ
GUQSH
HCIFZ
HG6
HMCUK
HVGLF
HZ~
IAO
ICQ
IEA
IEP
IGS
IH2
IHR
INH
INR
IOF
IPY
ISR
K6-
KB.
KOO
L6V
L7B
LGEZI
LK5
LK8
LOTEE
LSO
M0K
M1P
M2M
M2O
M2P
M7P
M7R
M7S
N9A
NADUK
NAPCQ
NEPJS
NXXTH
O9-
OBC
ODYON
OES
OHH
OMK
OVD
P2P
P62
PATMY
PCBAR
PDBOC
PKN
PQQKQ
PROAC
PSQYO
PSYQQ
PTHSS
PV9
PYCSY
Q2X
R05
RND
RNS
RNT
RNTTT
RXW
S0X
SC5
SHXYY
SIXXV
SJFOW
SJN
SNYQT
SOJ
TAE
TAOOD
TBHMF
TDRGL
TEORI
TN5
TSG
TWZ
U5U
UIG
UKHRP
UKR
UMD
UQL
VQA
VVN
WH7
WOW
X7M
XIH
XKW
XZL
Y6R
YAE
YCJ
YFH
YIF
YIN
YJ6
YNT
YOC
YQT
YR2
YR5
YXB
YZZ
Z5M
ZCA
~02
~7V
~88
~KM
AARCD
AAYXX
ABFSG
ACMFV
ACSTC
AEZWR
AFANA
AFHIU
AHWEU
AIXLP
ALPWD
ATHPR
CITATION
NFIDA
PHGZM
PHGZT
0WA
NPM
PJZUB
PPXIY
PQGLB
3V.
7QG
7QL
7QP
7QR
7SN
7SS
7ST
7T5
7TG
7TK
7TM
7TO
7U9
7XB
88A
8FD
8FK
AFKWF
C1K
FR3
H94
K9.
KL.
M7N
MBDVC
P64
PKEHL
PQEST
PQUKI
Q9U
RC3
SOI
TUS
7X8
1XC
UMC
VOOES
5PM
ID FETCH-LOGICAL-c509t-b77613f0a0a28f82a0c70e3becc7fa574b1a3ab5ec18ed07e147fe11ff791f5f3
IEDL.DBID C6C
ISSN 0028-0836
1476-4687
IngestDate Thu Aug 21 18:35:42 EDT 2025
Fri May 09 12:23:59 EDT 2025
Fri Jul 11 09:47:48 EDT 2025
Sat Aug 23 12:28:44 EDT 2025
Mon Jul 21 06:08:57 EDT 2025
Thu Apr 24 22:54:04 EDT 2025
Tue Jul 01 02:58:49 EDT 2025
Fri Feb 21 02:39:27 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7995
Language English
License 2023. The Author(s), under exclusive licence to Springer Nature Limited.
Attribution: http://creativecommons.org/licenses/by
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c509t-b77613f0a0a28f82a0c70e3becc7fa574b1a3ab5ec18ed07e147fe11ff791f5f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0009-0009-4976-4267
0000-0002-7466-7997
0000-0001-7341-1917
0000-0003-3604-3590
0000-0002-5552-9855
0000-0002-8470-8203
0000-0002-2200-901X
OpenAccessLink https://www.nature.com/articles/s41586-023-06924-6
PMID 38096900
PQID 2917332228
PQPubID 40569
PageCount 8
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_10794145
hal_primary_oai_HAL_hal_04682926v1
proquest_miscellaneous_2902955043
proquest_journals_2917332228
pubmed_primary_38096900
crossref_citationtrail_10_1038_s41586_023_06924_6
crossref_primary_10_1038_s41586_023_06924_6
springer_journals_10_1038_s41586_023_06924_6
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024-01-18
PublicationDateYYYYMMDD 2024-01-18
PublicationDate_xml – month: 01
  year: 2024
  text: 2024-01-18
  day: 18
PublicationDecade 2020
PublicationPlace London
PublicationPlace_xml – name: London
– name: England
PublicationSubtitle International weekly journal of science
PublicationTitle Nature (London)
PublicationTitleAbbrev Nature
PublicationTitleAlternate Nature
PublicationYear 2024
Publisher Nature Publishing Group UK
Nature Publishing Group
Publisher_xml – name: Nature Publishing Group UK
– name: Nature Publishing Group
References Millidge, B. Scaffolded LLMs as natural language computers. Beren’s Bloghttps://www.beren.io/2023-04-11-Scaffolded-LLMs-natural-language-computers (2023).
Ni, A. et al. Lever: learning to verify language-to-code generation with execution. In Proc.International Conference on Machine Learning 26106–26128 (PMLR, 2023).
RamananPBrownDJLeeC-CLeeD-TOn-line bin packing in linear timeJ. Algorithm.198910305326100698810.1016/0196-6774(89)90031-X
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).
Polu, S. & Sutskever, I. Generative language modeling for automated theorem proving. Preprint at https://arxiv.org/abs/2009.03393 (2020).
Code models overview. Vertex AI, Google Cloudhttps://cloud.google.com/vertex-ai/docs/generative-ai/code/code-models-overview (2023).
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).
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).
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 1–8 (IEEE, 2010).
PughJKSorosLBStanleyKOQuality diversity: a new frontier for evolutionary computationFront. Robotics AI201634010.3389/frobt.2016.00040
KozaJRGenetic programming as a means for programming computers by natural selectionStat. Comput.199448711210.1007/BF00175355
Coffman, E. G., Garey, M. R. & Johnson, D. S. in Algorithm Design for Computer System Design (eds Ausiello, G. et al.) 49–106 (Springer, 1984).
Mouret, J.-B. & Doncieux, S. Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In Proc. 2009 IEEE Congress on Evolutionary Computation 1161–1168 (IEEE, 2009).
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).
Naslund, E. & Sawin, W. Upper bounds for sunflower-free sets. Forum Math. Sigma5, e15 (2017).
GrochowJNew applications of the polynomial method: the cap set conjecture and beyondBull. Am. Math. Soc.20195629642019CMaPh.366...29G388614310.1090/bull/1648
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).
Croot, E., Lev, V. F. & Pach, P. P. Progression-free sets in are exponentially small. Ann. Math.185, 331–337 (2017).
MankowitzDJFaster sorting algorithms discovered using deep reinforcement learningNature20236182572632023Natur.618..257M1:CAS:528:DC%2BB3sXhtFOksrjK10.1038/s41586-023-06004-93728664910247365
Fried, D. et al. Incoder: a generative model for code infilling and synthesis. In Proc. International Conference on Learning Representations (2022).
Coffman, E. G., Csirik, J., Galambos, G., Martello, S. & Vigo, D. in Handbook of Combinatorial Optimization (eds Pardalos, P. M. et al.) 455–531 (Springer, 2013).
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).
Cameron, P. J. & Van Lint, J. H. Designs, Graphs, Codes and Their Links Vol. 3 (Cambridge Univ. Press, 1991).
Haluptzok, P., Bowers, M. & Kalai, A. T. Language models can teach themselves to program better. In International Conference on Learning Representations (2023).
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 1559–1565 (ACM, 2007).
EdelYBierbrauerJLarge caps in small spacesDes. Codes Cryptogr.200123197212183094110.1023/A:1011216716700
Wu, J. et al. Recursively summarizing books with human feedback. Preprint at https://arxiv.org/abs/2109.10862 (2021).
HelmuthTSpectorLMathesonJSolving uncompromising problems with lexicase selectionIEEE Trans. Evol. Comput.20151963064310.1109/TEVC.2014.2362729
LiYCompetition-level code generation with alphacodeScience2022378109210972022Sci...378.1092L1:CAS:528:DC%2BB38XjtVyhtrrJ10.1126/science.abq115836480631
Schick, T. et al. Toolformer: language models can teach themselves to use tools. Preprint at https://arxiv.org/abs/2302.04761 (2023).
Langdon, W. B. & Poli, R. Foundations of Genetic Programming (Springer Science & Business Media, 2013).
MaHNarayanaswamyARileyPLiLEvolving symbolic density functionalsSci. Adv.20228eabq02792022SciA....8..279M10.1126/sciadv.abq0279360839069462698
Beasley, J. E. OR-library: distributing test problems by electronic mail. J. Oper. Res. Soc.41, 1069–1072 (1990).
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).
OpenAI, GPT-4 technical report. Preprint at https://arxiv.org/abs/2303.08774 (2023).
Borji, A. A. categorical archive of ChatGPT failures. Preprint at https://arxiv.org/abs/2302.03494 (2023).
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).
ChaitinGJOn the length of programs for computing finite binary sequencesJ. ACM19661354756921052010.1145/321356.321363
HutterMLeggSFitness uniform optimizationIEEE Trans. Evol. Comput.20061056858910.1109/TEVC.2005.863127
Cantú-PazEA survey of parallel genetic algorithmsCalculateurs Paralleles, Reseaux et Systemes Repartis199810141171
Li, M. et al. An Introduction to Kolmogorov Complexity and its Applications Vol. 3 (Springer, 2008).
Yao, S. et al. ReAct: dynergizing reasoning and acting in language models. In Proc.International Conference on Learning Representations (2023).
SolomonoffRJA formal theory of inductive inference. Part IInf. Control1964712217274510.1016/S0019-9958(64)90223-2
O’NeillMVanneschiLGustafsonSBanzhafWOpen issues in genetic programmingGenet. Program. Evolvable Mach.20101133936310.1007/s10710-010-9113-2
Polu, S. et al. Formal mathematics statement curriculum learning. In International Conference on Learning Representations (2023).
Chen, M. et al. Evaluating large language models trained on code. Preprint at https://arxiv.org/abs/2107.03374 (2021).
Yin, P. et al. Natural language to code generation in interactive data science notebooks. Preprint at https://arxiv.org/abs/2212.09248 (2022).
Chen, X., Lin, M., Schärli, N. & Zhou, D. Teaching large language models to self-debug. Preprint at https://arxiv.org/abs/2304.05128 (2023).
SchmidtMLipsonHDistilling free-form natural laws from experimental dataScience200932481852009Sci...324...81S1:CAS:528:DC%2BD1MXjvVajsbw%3D10.1126/science.116589319342586
JiangAQTHOR: wielding hammers to integrate language models and automated theorem proversAdv. Neural Info. Process. Syst.20223583608373
Yang, F. et al. Launchpad: a programming model for distributed machine learning research. Preprint at https://arxiv.org/abs/2106.04516 (2021).
Tao, T. Open question: best bounds for cap sets. WordPress Bloghttps://terrytao.wordpress.com/2007/02/23/open-question-best-bounds-for-cap-sets/ (2009).
SeidenSSOn the online bin packing problemJ. ACM200249640671214709510.1145/585265.585269
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 2530–2537 (IEEE, 2007).
SchkufzaESharmaRAikenAStochastic superoptimizationACM SIGARCH Comp. Archit. News20134130531610.1145/2490301.2451150
Meyerson, E. et al. Language model crossover: variation through few-shot prompting. Preprint at https://arxiv.org/abs/2302.12170 (2023).
Balogh, J., Békési, J., Dósa, 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.) 1425–1438 (SIAM, 2014).
Tyrrell, F. New lower bounds for cap sets. Discrete Analysishttps://doi.org/10.19086/da.91076 (2023).
Shypula, A. et al. Learning to superoptimize real-world programs. In Proc. Deep Learning for Code Workshop (ICLR 2022 Workshop) (2022).
FawziADiscovering faster matrix multiplication algorithms with reinforcement learningNature202261047532022Natur.610...47F1:CAS:528:DC%2BB38XisFygurfK10.1038/s41586-022-05172-4361987809534758
EdelYExtensions of generalized product capsDes. Codes Cryptogr.200431514203169410.1023/A:1027365901231
Koza, J. R. Genetic Programming II: Automatic Discovery of Reusable Programs (MIT, 1994).
Ellenberg, J. S., Gijswijt, D. On large subsets of Fqn\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${F}_{q}^{n}$$\end{document} with no three-term arithmetic progression. Ann. Math.185, 339–343 (2017).
HillROn the largest size of cap in S5,3Rend Lincei. Sci. Fis. Mat. Nat.197354378384363951
ZelikmanEWuYMuJGoodmanNStar: bootstrapping reasoning with reasoningAdv. Neural Info. Process. Syst.2022351547615488
Lehman, J. et al. in Handbook of Evolutionary Machine Learning (eds Banzhaf, W. et al.) 331–366 (Springer, 2023).
Anil, R. et al. Palm 2 technical report. Preprint at https://arxiv.org/abs/2305.10403 (2023).
Chen, X. et al. Symbolic discovery of optimization algorithms. Preprint at https://arxiv.org/abs/2302.06675 (2023).
BurkeEKHyper-heuristics: a survey of the state of the artJ. Oper. Res. Soc.2013641695172410.1057/jors.2013.71
Goldberg, D. E. Genetic Algorithms in Search, Optimization and
SS Seiden (6924_CR42) 2002; 49
6924_CR60
6924_CR61
6924_CR62
6924_CR63
6924_CR20
GJ Chaitin (6924_CR48) 1966; 13
6924_CR64
6924_CR65
6924_CR22
6924_CR66
6924_CR23
6924_CR24
JK Pugh (6924_CR56) 2016; 3
6924_CR68
6924_CR25
6924_CR69
6924_CR26
6924_CR27
6924_CR29
EK Burke (6924_CR81) 2013; 64
A Fawzi (6924_CR89) 2022; 610
Y Edel (6924_CR33) 2001; 23
RJ Solomonoff (6924_CR50) 1964; 7
6924_CR91
J Grochow (6924_CR21) 2019; 56
6924_CR52
6924_CR53
6924_CR10
CC Lee (6924_CR40) 1985; 32
Y Edel (6924_CR34) 2004; 31
6924_CR55
6924_CR12
6924_CR13
6924_CR14
6924_CR9
6924_CR59
6924_CR16
6924_CR17
M Schmidt (6924_CR75) 2009; 324
6924_CR6
6924_CR18
P Ramanan (6924_CR41) 1989; 10
6924_CR5
6924_CR19
6924_CR8
6924_CR7
6924_CR2
6924_CR1
E Cantú-Paz (6924_CR28) 1998; 10
6924_CR4
6924_CR3
6924_CR80
S Martello (6924_CR46) 1990; 28
6924_CR82
6924_CR83
M Hutter (6924_CR58) 2006; 10
6924_CR84
6924_CR85
R Hill (6924_CR35) 1973; 54
6924_CR86
DJ Mankowitz (6924_CR90) 2023; 618
6924_CR43
6924_CR44
6924_CR88
6924_CR45
R Salustowicz (6924_CR78) 1997; 5
6924_CR47
6924_CR49
T Helmuth (6924_CR57) 2015; 19
AR Calderbank (6924_CR37) 1994; 4
E Schkufza (6924_CR87) 2013; 41
Y Li (6924_CR11) 2022; 378
H Ma (6924_CR74) 2022; 8
6924_CR70
6924_CR71
M O’Neill (6924_CR51) 2010; 11
6924_CR72
6924_CR73
6924_CR30
6924_CR31
6924_CR32
6924_CR76
AQ Jiang (6924_CR54) 2022; 35
6924_CR77
E Zelikman (6924_CR67) 2022; 35
6924_CR79
6924_CR36
6924_CR38
6924_CR39
JR Koza (6924_CR15) 1994; 4
References_xml – reference: Tao, T. & Vu, V. H. Additive Combinatorics Vol. 105 (Cambridge Univ. Press, 2006).
– reference: Beasley, J. E. OR-library: distributing test problems by electronic mail. J. Oper. Res. Soc.41, 1069–1072 (1990).
– reference: JiangAQTHOR: wielding hammers to integrate language models and automated theorem proversAdv. Neural Info. Process. Syst.20223583608373
– reference: 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).
– reference: MankowitzDJFaster sorting algorithms discovered using deep reinforcement learningNature20236182572632023Natur.618..257M1:CAS:528:DC%2BB3sXhtFOksrjK10.1038/s41586-023-06004-93728664910247365
– reference: Cantú-PazEA survey of parallel genetic algorithmsCalculateurs Paralleles, Reseaux et Systemes Repartis199810141171
– reference: Croot, E., Lev, V. F. & Pach, P. P. Progression-free sets in are exponentially small. Ann. Math.185, 331–337 (2017).
– reference: Park, J. S. et al. Generative agents: interactive simulacra of human behavior. In Proc. 36th Annual ACM Symposium on User Interface Software and Technology1–22 (ACM, 2023).
– reference: SchmidtMLipsonHDistilling free-form natural laws from experimental dataScience200932481852009Sci...324...81S1:CAS:528:DC%2BD1MXjvVajsbw%3D10.1126/science.116589319342586
– reference: Lehman, J. et al. in Handbook of Evolutionary Machine Learning (eds Banzhaf, W. et al.) 331–366 (Springer, 2023).
– reference: BurkeEKHyper-heuristics: a survey of the state of the artJ. Oper. Res. Soc.2013641695172410.1057/jors.2013.71
– reference: Shypula, A. et al. Learning to superoptimize real-world programs. In Proc. Deep Learning for Code Workshop (ICLR 2022 Workshop) (2022).
– reference: 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).
– reference: SeidenSSOn the online bin packing problemJ. ACM200249640671214709510.1145/585265.585269
– reference: FawziADiscovering faster matrix multiplication algorithms with reinforcement learningNature202261047532022Natur.610...47F1:CAS:528:DC%2BB38XisFygurfK10.1038/s41586-022-05172-4361987809534758
– reference: Balogh, J., Békési, J., Dósa, G., Epstein, L. & Levin, A. A new and improved algorithm for online bin packing. In Proc.26th Annual European Symposium on Algorithms (ESA 2018) 5:1–5:14 (Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2018).
– reference: Ni, A. et al. Lever: learning to verify language-to-code generation with execution. In Proc.International Conference on Machine Learning 26106–26128 (PMLR, 2023).
– reference: Coffman, E. G., Csirik, J., Galambos, G., Martello, S. & Vigo, D. in Handbook of Combinatorial Optimization (eds Pardalos, P. M. et al.) 455–531 (Springer, 2013).
– reference: Mouret, J.-B. & Doncieux, S. Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In Proc. 2009 IEEE Congress on Evolutionary Computation 1161–1168 (IEEE, 2009).
– reference: 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).
– reference: Chen, X. et al. Symbolic discovery of optimization algorithms. Preprint at https://arxiv.org/abs/2302.06675 (2023).
– reference: Schick, T. et al. Toolformer: language models can teach themselves to use tools. Preprint at https://arxiv.org/abs/2302.04761 (2023).
– reference: Li, R. et al. StarCoder: may the source be with you! Preprint at https://arxiv.org/abs/2305.06161 (2023).
– reference: CalderbankARFishburnPCMaximal three-independent subsets of {0, 1, 2} nDes. Codes Cryptogr.19944203211127794010.1007/BF01388452
– reference: Koza, J. R. Genetic Programming II: Automatic Discovery of Reusable Programs (MIT, 1994).
– reference: SalustowiczRSchmidhuberJProbabilistic incremental program evolutionEvol. Comput.199751231411:STN:280:DC%2BC2sfnvVamtg%3D%3D10.1162/evco.1997.5.2.12310021756
– reference: 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).
– reference: Chen, M. et al. Evaluating large language models trained on code. Preprint at https://arxiv.org/abs/2107.03374 (2021).
– reference: Angelopoulos, S., Kamali, S. & Shadkami, K. Online bin packing with predictions. J. Artif. Intell.Res.36, 4574–4580 (2022).
– reference: KozaJRGenetic programming as a means for programming computers by natural selectionStat. Comput.199448711210.1007/BF00175355
– reference: Tao, T. Open question: best bounds for cap sets. WordPress Bloghttps://terrytao.wordpress.com/2007/02/23/open-question-best-bounds-for-cap-sets/ (2009).
– reference: Fried, D. et al. Incoder: a generative model for code infilling and synthesis. In Proc. International Conference on Learning Representations (2022).
– reference: MartelloSTothPLower bounds and reduction procedures for the bin packing problemDiscrete Appl. Math.1990285970106483110.1016/0166-218X(90)90094-S
– reference: Yang, F. et al. Launchpad: a programming model for distributed machine learning research. Preprint at https://arxiv.org/abs/2106.04516 (2021).
– reference: Tanese, R. Distributed Genetic Algorithms for Function Optimization. PhD thesis, Univ. Michigan (1989).
– reference: Ross, P. in Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques (eds Burke, E. K. & Kendall, G.) 529–556 (Springer, 2005).
– reference: RamananPBrownDJLeeC-CLeeD-TOn-line bin packing in linear timeJ. Algorithm.198910305326100698810.1016/0196-6774(89)90031-X
– reference: SchkufzaESharmaRAikenAStochastic superoptimizationACM SIGARCH Comp. Archit. News20134130531610.1145/2490301.2451150
– reference: Castiñeiras, I., De Cauwer, M. & O’Sullivan, B. Weibull-based benchmarks for bin packing. In Proc.International Conference on Principles and Practice of Constraint Programming 207–222 (Springer, 2012).
– reference: Liventsev, V., Grishina, A., Härmä, A. & Moonen, L. Fully autonomous programming with large language models. Preprint at https://arxiv.org/abs/2304.10423 (2023).
– reference: HillROn the largest size of cap in S5,3Rend Lincei. Sci. Fis. Mat. Nat.197354378384363951
– reference: Cameron, P. J. & Van Lint, J. H. Designs, Graphs, Codes and Their Links Vol. 3 (Cambridge Univ. Press, 1991).
– reference: 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).
– reference: LeeCCLeeDTA simple on-line bin-packing algorithmJ. ACM19853256257279620110.1145/3828.3833
– reference: 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 860–869 (Springer, 2006).
– reference: Goldberg, D. E. Genetic Algorithms in Search, Optimization and Machine Learning (Addison-Wesley, 1989).
– reference: Coffman, E. G., Garey, M. R. & Johnson, D. S. in Algorithm Design for Computer System Design (eds Ausiello, G. et al.) 49–106 (Springer, 1984).
– reference: MaHNarayanaswamyARileyPLiLEvolving symbolic density functionalsSci. Adv.20228eabq02792022SciA....8..279M10.1126/sciadv.abq0279360839069462698
– reference: GrochowJNew applications of the polynomial method: the cap set conjecture and beyondBull. Am. Math. Soc.20195629642019CMaPh.366...29G388614310.1090/bull/1648
– reference: Ellenberg, J. S., Gijswijt, D. On large subsets of Fqn\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${F}_{q}^{n}$$\end{document} with no three-term arithmetic progression. Ann. Math.185, 339–343 (2017).
– reference: Madaan, A. et al. Learning performance-improving code edits. Preprint at https://arxiv.org/abs/2302.07867 (2023).
– reference: PughJKSorosLBStanleyKOQuality diversity: a new frontier for evolutionary computationFront. Robotics AI201634010.3389/frobt.2016.00040
– reference: 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).
– reference: Burke, E. et al. in Handbook of Metaheuristics (eds Glover, F. & Kochenberger, G. A.) 457–474 (Springer, 2003).
– reference: LiYCompetition-level code generation with alphacodeScience2022378109210972022Sci...378.1092L1:CAS:528:DC%2BB38XjtVyhtrrJ10.1126/science.abq115836480631
– reference: Borji, A. A. categorical archive of ChatGPT failures. Preprint at https://arxiv.org/abs/2302.03494 (2023).
– reference: O’NeillMVanneschiLGustafsonSBanzhafWOpen issues in genetic programmingGenet. Program. Evolvable Mach.20101133936310.1007/s10710-010-9113-2
– reference: Haluptzok, P., Bowers, M. & Kalai, A. T. Language models can teach themselves to program better. In International Conference on Learning Representations (2023).
– reference: 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).
– reference: SolomonoffRJA formal theory of inductive inference. Part IInf. Control1964712217274510.1016/S0019-9958(64)90223-2
– reference: Polu, S. et al. Formal mathematics statement curriculum learning. In International Conference on Learning Representations (2023).
– reference: HelmuthTSpectorLMathesonJSolving uncompromising problems with lexicase selectionIEEE Trans. Evol. Comput.20151963064310.1109/TEVC.2014.2362729
– reference: Polu, S. & Sutskever, I. Generative language modeling for automated theorem proving. Preprint at https://arxiv.org/abs/2009.03393 (2020).
– reference: 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 1559–1565 (ACM, 2007).
– reference: Tyrrell, F. New lower bounds for cap sets. Discrete Analysishttps://doi.org/10.19086/da.91076 (2023).
– reference: 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).
– reference: EdelYExtensions of generalized product capsDes. Codes Cryptogr.200431514203169410.1023/A:1027365901231
– reference: 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 2530–2537 (IEEE, 2007).
– reference: OpenAI, GPT-4 technical report. Preprint at https://arxiv.org/abs/2303.08774 (2023).
– reference: Zheng, M. et al. Can GPT-4 perform neural architecture search? Preprint at https://arxiv.org/abs/2304.10970 (2023).
– reference: Wang, G. et al. Voyager: an open-ended embodied agent with large language models. Preprint at https://arxiv.org/abs/2305.16291 (2023).
– reference: ZelikmanEWuYMuJGoodmanNStar: bootstrapping reasoning with reasoningAdv. Neural Info. Process. Syst.2022351547615488
– reference: HutterMLeggSFitness uniform optimizationIEEE Trans. Evol. Comput.20061056858910.1109/TEVC.2005.863127
– reference: Naslund, E. & Sawin, W. Upper bounds for sunflower-free sets. Forum Math. Sigma5, e15 (2017).
– reference: Wu, J. et al. Recursively summarizing books with human feedback. Preprint at https://arxiv.org/abs/2109.10862 (2021).
– reference: Balogh, J., Békési, J., Dósa, 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.) 1425–1438 (SIAM, 2014).
– reference: Li, M. et al. An Introduction to Kolmogorov Complexity and its Applications Vol. 3 (Springer, 2008).
– reference: Code models overview. Vertex AI, Google Cloudhttps://cloud.google.com/vertex-ai/docs/generative-ai/code/code-models-overview (2023).
– reference: 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 1–8 (IEEE, 2010).
– reference: Meyerson, E. et al. Language model crossover: variation through few-shot prompting. Preprint at https://arxiv.org/abs/2302.12170 (2023).
– reference: Chen, X., Lin, M., Schärli, N. & Zhou, D. Teaching large language models to self-debug. Preprint at https://arxiv.org/abs/2304.05128 (2023).
– reference: Bunel, R., Desmaison, A., Kohli, P., Torr, P. H. & Kumar, M. P. Learning to superoptimize programs. In Proc.International Conference on Learning Representations (2017).
– reference: Langdon, W. B. & Poli, R. Foundations of Genetic Programming (Springer Science & Business Media, 2013).
– reference: Anil, R. et al. Palm 2 technical report. Preprint at https://arxiv.org/abs/2305.10403 (2023).
– reference: 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).
– reference: ChaitinGJOn the length of programs for computing finite binary sequencesJ. ACM19661354756921052010.1145/321356.321363
– reference: Millidge, B. Scaffolded LLMs as natural language computers. Beren’s Bloghttps://www.beren.io/2023-04-11-Scaffolded-LLMs-natural-language-computers (2023).
– reference: Yao, S. et al. ReAct: dynergizing reasoning and acting in language models. In Proc.International Conference on Learning Representations (2023).
– reference: EdelYBierbrauerJLarge caps in small spacesDes. Codes Cryptogr.200123197212183094110.1023/A:1011216716700
– reference: Austin, J. et al. Program synthesis with large language models. Preprint at https://arxiv.org/abs/2108.07732 (2021).
– reference: Yin, P. et al. Natural language to code generation in interactive data science notebooks. Preprint at https://arxiv.org/abs/2212.09248 (2022).
– ident: 6924_CR10
  doi: 10.1145/3583131.3590481
– volume: 618
  start-page: 257
  year: 2023
  ident: 6924_CR90
  publication-title: Nature
  doi: 10.1038/s41586-023-06004-9
– ident: 6924_CR29
– ident: 6924_CR60
– ident: 6924_CR25
– ident: 6924_CR84
  doi: 10.1109/CEC.2010.5586388
– ident: 6924_CR77
– volume: 49
  start-page: 640
  year: 2002
  ident: 6924_CR42
  publication-title: J. ACM
  doi: 10.1145/585265.585269
– volume: 13
  start-page: 547
  year: 1966
  ident: 6924_CR48
  publication-title: J. ACM
  doi: 10.1145/321356.321363
– volume: 378
  start-page: 1092
  year: 2022
  ident: 6924_CR11
  publication-title: Science
  doi: 10.1126/science.abq1158
– ident: 6924_CR47
  doi: 10.24963/ijcai.2022/635
– ident: 6924_CR68
– ident: 6924_CR22
  doi: 10.1017/CBO9780511755149
– ident: 6924_CR39
  doi: 10.1007/978-3-7091-4338-4_3
– ident: 6924_CR73
– ident: 6924_CR64
– volume: 4
  start-page: 203
  year: 1994
  ident: 6924_CR37
  publication-title: Des. Codes Cryptogr.
  doi: 10.1007/BF01388452
– volume: 324
  start-page: 81
  year: 2009
  ident: 6924_CR75
  publication-title: Science
  doi: 10.1126/science.1165893
– ident: 6924_CR12
– volume: 56
  start-page: 29
  year: 2019
  ident: 6924_CR21
  publication-title: Bull. Am. Math. Soc.
  doi: 10.1090/bull/1648
– volume: 8
  start-page: eabq0279
  year: 2022
  ident: 6924_CR74
  publication-title: Sci. Adv.
  doi: 10.1126/sciadv.abq0279
– ident: 6924_CR9
– ident: 6924_CR59
– ident: 6924_CR45
  doi: 10.1007/978-1-4419-7997-1_35
– volume: 5
  start-page: 123
  year: 1997
  ident: 6924_CR78
  publication-title: Evol. Comput.
  doi: 10.1162/evco.1997.5.2.123
– volume: 610
  start-page: 47
  year: 2022
  ident: 6924_CR89
  publication-title: Nature
  doi: 10.1038/s41586-022-05172-4
– ident: 6924_CR61
– volume: 41
  start-page: 305
  year: 2013
  ident: 6924_CR87
  publication-title: ACM SIGARCH Comp. Archit. News
  doi: 10.1145/2490301.2451150
– ident: 6924_CR76
– volume: 32
  start-page: 562
  year: 1985
  ident: 6924_CR40
  publication-title: J. ACM
  doi: 10.1145/3828.3833
– volume: 10
  start-page: 305
  year: 1989
  ident: 6924_CR41
  publication-title: J. Algorithm.
  doi: 10.1016/0196-6774(89)90031-X
– ident: 6924_CR91
  doi: 10.1155/2021/6593438
– volume: 10
  start-page: 141
  year: 1998
  ident: 6924_CR28
  publication-title: Calculateurs Paralleles, Reseaux et Systemes Repartis
– volume: 23
  start-page: 197
  year: 2001
  ident: 6924_CR33
  publication-title: Des. Codes Cryptogr.
  doi: 10.1023/A:1011216716700
– ident: 6924_CR69
– ident: 6924_CR17
– ident: 6924_CR49
  doi: 10.1007/978-0-387-49820-1
– ident: 6924_CR72
– ident: 6924_CR65
– ident: 6924_CR44
– ident: 6924_CR19
  doi: 10.1145/3638529.3654017
– ident: 6924_CR13
– ident: 6924_CR86
– ident: 6924_CR6
– ident: 6924_CR3
  doi: 10.1007/978-981-99-3814-8_11
– ident: 6924_CR8
– volume: 4
  start-page: 87
  year: 1994
  ident: 6924_CR15
  publication-title: Stat. Comput.
  doi: 10.1007/BF00175355
– ident: 6924_CR79
– ident: 6924_CR2
  doi: 10.21203/rs.3.rs-2895792/v1
– ident: 6924_CR27
– ident: 6924_CR52
– ident: 6924_CR16
  doi: 10.1145/3694791
– ident: 6924_CR24
  doi: 10.1007/978-3-642-33558-7_17
– ident: 6924_CR38
  doi: 10.19086/da.91076
– ident: 6924_CR62
– ident: 6924_CR30
  doi: 10.4007/annals.2017.185.1.7
– volume: 28
  start-page: 59
  year: 1990
  ident: 6924_CR46
  publication-title: Discrete Appl. Math.
  doi: 10.1016/0166-218X(90)90094-S
– volume: 35
  start-page: 8360
  year: 2022
  ident: 6924_CR54
  publication-title: Adv. Neural Info. Process. Syst.
– volume: 19
  start-page: 630
  year: 2015
  ident: 6924_CR57
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2014.2362729
– ident: 6924_CR23
  doi: 10.1038/sj/jors/0411109
– ident: 6924_CR20
– ident: 6924_CR66
– ident: 6924_CR32
  doi: 10.1017/fms.2017.12
– ident: 6924_CR18
– ident: 6924_CR71
– volume: 35
  start-page: 15476
  year: 2022
  ident: 6924_CR67
  publication-title: Adv. Neural Info. Process. Syst.
– ident: 6924_CR14
– ident: 6924_CR1
– volume: 7
  start-page: 1
  year: 1964
  ident: 6924_CR50
  publication-title: Inf. Control
  doi: 10.1016/S0019-9958(64)90223-2
– ident: 6924_CR5
– ident: 6924_CR7
– volume: 31
  start-page: 5
  year: 2004
  ident: 6924_CR34
  publication-title: Des. Codes Cryptogr.
  doi: 10.1023/A:1027365901231
– ident: 6924_CR43
  doi: 10.1137/1.9781611973730.94
– ident: 6924_CR80
– volume: 54
  start-page: 378
  year: 1973
  ident: 6924_CR35
  publication-title: Rend Lincei. Sci. Fis. Mat. Nat.
– ident: 6924_CR53
– ident: 6924_CR26
– ident: 6924_CR55
  doi: 10.1109/CEC.2009.4983077
– ident: 6924_CR82
  doi: 10.1007/11844297_87
– volume: 11
  start-page: 339
  year: 2010
  ident: 6924_CR51
  publication-title: Genet. Program. Evolvable Mach.
  doi: 10.1007/s10710-010-9113-2
– volume: 10
  start-page: 568
  year: 2006
  ident: 6924_CR58
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2005.863127
– ident: 6924_CR85
  doi: 10.1109/CEC.2007.4424789
– ident: 6924_CR63
  doi: 10.1145/3586183.3606763
– ident: 6924_CR70
– volume: 3
  start-page: 40
  year: 2016
  ident: 6924_CR56
  publication-title: Front. Robotics AI
  doi: 10.3389/frobt.2016.00040
– volume: 64
  start-page: 1695
  year: 2013
  ident: 6924_CR81
  publication-title: J. Oper. Res. Soc.
  doi: 10.1057/jors.2013.71
– ident: 6924_CR88
– ident: 6924_CR83
  doi: 10.1145/1276958.1277273
– ident: 6924_CR31
  doi: 10.4007/annals.2017.185.1.8
– ident: 6924_CR36
  doi: 10.1017/CBO9780511623714
– ident: 6924_CR4
SSID ssj0005174
Score 2.748454
Snippet Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language....
Large Language Models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language....
Abstract Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural...
SourceID pubmedcentral
hal
proquest
pubmed
crossref
springer
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 468
SubjectTerms 639/705/1045
639/705/117
Algorithms
Applications programs
Artificial Intelligence
Combinatorial analysis
Combinatorics
Computer Science
Design specifications
Feedback loops
Function space
Humanities and Social Sciences
Language
Large language models
Mathematical models
multidisciplinary
Natural language (computers)
Neural networks
Science
Science (multidisciplinary)
Subject specialists
Task complexity
SummonAdditionalLinks – databaseName: ProQuest Technology Collection
  dbid: 8FG
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwEB7RIiQuiJZXoCCDOIAgqh3HiX1CFWK7QpQTlXqzHMdWK1XZQrb8fmYSJ6ttRa-Jozj5PJ7X5xmA91EE3bom5k6amFPBrlwjzLlonTHRKyEdnUY--VktT8vvZ-osBdz6RKuc9sRho25XnmLkhwX6FZLSAvrL1e-cukZRdjW10NiB-wI1DVG69OJ4Q_G4UYU5HZrhUh_2qLg00W-ptwH6IHm1pZh2zokWedvmvE2dvJE_HdTS4jE8SvYkOxoXwB7cC90-PBh4nb7fh70kuz37kApMf3wCxydzrVZ8lM7lEo8TXWZGh01YomyxUQgYRWrZJRHG2RTcZEP_nP4pnC6-_fq6zFNDhdyjXbDOm7pG7R25467QUReO-5oHSTDW0am6bIRDbFTwQoeW10GUdQxCxFgbEVWUz2C3W3XhBTAfRdMaXsXGuzLKqnE-OFN45akPqtIZiOlvWp-qjVPTi0s7ZL2ltiMCFhGwAwK2yuDT_MzVWGvjztHvEKR5IJXJXh79sHQNfX5dmKL6KzI4mDC0STh7u1lKGbydb6NYUa7EdWF1TWN4YRSVd8vg-Qj5_Cqp0e8znGegtxbD1ly273QX50PpbnS2TSlKlcHnad1s5vX_b31592e8gocF2loUGRL6AHbXf67Da7SV1s2bQSD-Ae78D-k
  priority: 102
  providerName: ProQuest
Title Mathematical discoveries from program search with large language models
URI https://link.springer.com/article/10.1038/s41586-023-06924-6
https://www.ncbi.nlm.nih.gov/pubmed/38096900
https://www.proquest.com/docview/2917332228
https://www.proquest.com/docview/2902955043
https://hal.science/hal-04682926
https://pubmed.ncbi.nlm.nih.gov/PMC10794145
Volume 625
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB51WyFxQbS8UsrKIA4giGrnZftYVt2uEK0QotLeLMdrq0hVipotv58Z51FtC0hcckjsxMlnxzP2N98AvA3Cq5WtQ2pzHVIS7EoVwpyKldU6uFLklqKRT8-qxXnxeVkutyAbYmEiaT9KWsbf9MAOO2xxolFEl6VcBOgzpNUEdki6nRyuWTW7pXXcUV7uA2V4rv5wj43JaHJBVMj7duZ9uuSdPdM4Fc0fw6PehmRHXat3Ycs3e_Agcjlduwe7_Xht2bteVPr9Ezg5HfVZsSrF4hJ3E91kRgEmrKdpsa7jM1qdZZdEEmfDgiaLOXPap3A-P_4-W6R9EoXUoS2wTmspccYO3HKbqaAyy53kPifoZLClLGphEY_SO6H8iksvChm8ECFILUIZ8mew3Vw1_gUwF0S90rwKtbNFyKvaOm915kpHuU9LlYAYvqZxvcI4Jbq4NHGnO1emQ8AgAiYiYKoEPox1fnb6Gv8s_QZBGguSNPbi6Iuhc-jnq0xn1S-RwMGAoekHZGsydEtz2lXCVr4eL-NQov0R2_irGyrDM12SpFsCzzvIx0flCn09zXkCaqMzbLRl80rz4yLKdaODrQtRlAl8HPrNbbv-_q77_1f8JTzM0N6i1SGhDmB7fX3jX6G9tK6nMJFLiUc1E3Scn0xh59Px2ddv0zh0fgPu0RH3
linkProvider Springer Nature
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEB61RQguiJZXoIBBIIEgqh952AeEKmC7pbs9tVJvxnFstVKVbckWxJ_iN-LJa7Wt6K3XjZO1PWOPx_PNNwBvPHOyNIWPjVA-RsKuWAYxx6w0SnmbMmEwG3m6n40Pk-9H6dEK_O1zYRBW2e-JzUZdzizekW_x4FcIDAvIz2fnMVaNwuhqX0KjVYs99-d3cNnqT7tfg3zfcj76dvBlHHdVBWIbjOM8LvLguQtPDTVceskNtTl1AseSe5PmScFM6GDqLJOupLljSe4dY97nivnUi_DdVbiViGDJMTN9tLOAlFxife6SdKiQW3UwlBLhvlhLIfg8cbZkCFePEYZ59Yx7Fap5KV7bmMHRfbjXnV_Jdqtw67Diqg243eBIbb0B691eUZN3HaH1-wewMx24YcOrmAeMuNHgohNMbiEdRIy0s0vwZpicIkCd9JeppKnXUz-EwxuZ6kewVs0q9wSI9awoFc18YU3iRVYY64ziNrVYdzWVEbB-NrXt2M2xyMapbqLsQupWAjpIQDcS0FkEH4Z3zlpuj2tbvw5CGhoiLfd4e6LxN5pkkiue_WIRbPYy1N1mUOuF6kbwangcljHGZkzlZhfYhnKVIp1cBI9bkQ9_JWTwMxWlEcglZVjqy_KT6uS4oQoPzr1KWJJG8LHXm0W__j_Wp9cP4yXcGR9MJ3qyu7_3DO7ycM7DWykmN2Ft_vPCPQ_ntHnxolkcBH7c9Gr8BwhBTls
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEB61RSAuiJZXoIBBIIEgWj_ysA8IVS3Llj7EgUq9Bcdrq0hVtpAtiL_Gr2Mmr7Kt6K3XjZO1PTO2x_PNNwAvgvB6assQW2VCTIRdsUYxx2JqjQkuFcpSNvLefjY5SD4dpodL8KfPhSFYZb8mNgv1dObojnwk0a9QFBbQo9DBIj5vjd-ffI-pghRFWvtyGq2K7Pjfv9B9q99tb6GsX0o5_vBlcxJ3FQZihxvlPC5z9OJV4JZbqYOWlruce0XjyoNN86QUFjubeie0n_LciyQPXogQciNCGhR-dxmu5SrXZGN68x94yTkG6C5hhys9qnHT1AT9pboK6P_E2cKmuHxEkMyL592LsM1zsdtmSxzfhlvdWZZttMq3Cku-WoPrDabU1Wuw2q0bNXvVkVu_vgMf9waeWHyVcoIJQ4ruOqNEF9bBxVg7u4xuidkxgdVZf7HKmto99V04uJKpvgcr1azyD4C5IMqp4VkonU2CykrrvDXSpY5qsKY6AtHPZuE6pnMquHFcNBF3pYtWAgVKoGgkUGQRvBneOWl5Pi5t_RyFNDQkiu7Jxm5Bv_Ek09LI7KeIYL2XYdEtDHVxpsYRPBseo0lTnMZWfnZKbbg0KVHLRXC_FfnwV0qjz2k4j0AvKMNCXxafVN-OGtpwdPRNIpI0gre93pz16_9jfXj5MJ7CDbTDYnd7f-cR3JR45KMLKqHXYWX-49Q_xiPbvHzS2AaDr1dtjH8BQiJSXA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Mathematical+discoveries+from+program+search+with+large+language+models&rft.jtitle=Nature+%28London%29&rft.au=Romera-Paredes%2C+Bernardino&rft.au=Barekatain%2C+Mohammadamin&rft.au=Novikov%2C+Alexander&rft.au=Balog%2C+Matej&rft.date=2024-01-18&rft.pub=Nature+Publishing+Group+UK&rft.issn=0028-0836&rft.eissn=1476-4687&rft.volume=625&rft.issue=7995&rft.spage=468&rft.epage=475&rft_id=info:doi/10.1038%2Fs41586-023-06924-6&rft_id=info%3Apmid%2F38096900&rft.externalDocID=PMC10794145
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0028-0836&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0028-0836&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0028-0836&client=summon