DreamCoder: bootstrapping inductive program synthesis with wake-sleep library learning
Open accessAbstract
We present a system for inductive program synthesis called DreamCoder, which inputs a corpus of synthesis problems each specified by one or a few examples, and automatically derives a library of program components and a neural search policy that can be used to efficiently solve other similar synthesis problems. The library and search policy bootstrap each other iteratively through a variant of "wake-sleep" approximate Bayesian learning. A new refactoring algorithm based on E-graph matching identifies common sub-components across synthesized programs, building a progressively deepening library of abstractions capturing the structure of the input domain. We evaluate on eight domains including classic program synthesis areas and AI tasks such as planning, inverse graphics, and equation discovery. We show that jointly learning the library and neural search policy leads to solving more problems, and solving them more quickly.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
An external generative model that created dream-like input helped train a DNN to produce the code behind a given mathematical mapping.
“Indeed, recently an external generative model that created “dream-like” input helped train a DNN to produce the code behind a given mathematical mapping.148”
From The overfitted brain: Dreams evolved to assist generalization (2021) · cites this paper as [148]
The evidence for the possibility that dreams improve performance comes from common methods in deep learning that improve generalization, such as dropout, domain randomization, and the use of input data created by stochastic stimulation of generative models, which together bear striking similarities to the properties of dreams.
“The evidence for this possibility comes from common methods in deep learning that improve generalization, such as dropout,126 domain randomization,144 and the use of input data created by stochastic stimulation of generative models,148 which together bear striking similarities to the properties of dreams.”
From The overfitted brain: Dreams evolved to assist generalization (2021) · cites this paper as [148]
Cites
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · see citing works
Prototypical Networks for Few-shot LearningPreprint
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 5,863 · see citing works
Categorization and Representation of Physics Problems by Experts and Novices*
Chi, M. T. H., Feltovich, P. J., & Glaser, R. (1981) · Cognitive Science · doi:10.1207/s15516709cog0502_2 · Cited by 5,248 · see citing works
Distilling Free-Form Natural Laws from Experimental Data
Schmidt, M., & Lipson, H. (2009) · Science · doi:10.1126/science.1165893 · Cited by 3,327 · see citing works
Domain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · cited 1× · see citing works
“8E), compositionally recombining latent building blocks and motifs acquired from the training data in ways never seen in its waking experience, but ideal for training a broadly generalizable recognition model [55].”
BackgroundBetween MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Sutton, R. S., Precup, D., & Singh, S. (1999) · Artificial Intelligence · doi:10.1016/s0004-3702(99)00052-1 · Cited by 3,119 · see citing works
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · see citing works
Self-citationPattern recognition and machine learning
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5091 · Cited by 2,782 · see citing works
Types and Programming Languages
Pierce, B. C. (2002) · Cited by 2,226 · see citing works
(2014) · doi:10.4324/9781315799681 · Cited by 2,174 · see citing works
Recursive functions of symbolic expressions and their computation by machine, Part I
McCarthy, J. (1960) · Communications of the ACM · doi:10.1145/367177.367199 · Cited by 1,635 · see citing works
Principal type-schemes for functional programs
Damas, L., & Milner, R. (1982) · ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · doi:10.1145/582153.582176 · Cited by 1,100 · see citing works
The "Wake-Sleep" Algorithm for Unsupervised Neural Networks
Hinton, G. E., Dayan, P., Frey, B. J., & Neal, R. M. (1995) · Science · doi:10.1126/science.7761831 · Cited by 1,070 · see citing works
Automating string processing in spreadsheets using input-output examples
Gulwani, S. (2011) · ACM-SIGACT Symposium on Principles of Programming Languages · doi:10.1145/1926385.1926423 · Cited by 1,039 · see citing works
Scientific Discovery: Computational Explorations of the Creative Processes
Pat Langley, B., Simon, H. A., Bradshaw, G. L., & Żytkow, J. M. (1987) · Medical Entomology and Zoology · Cited by 802 · see citing works
Simplify: a theorem prover for program checking
Detlefs, D., Nelson, G., & Saxe, J. B. (2005) · Journal of the ACM · doi:10.1145/1066100.1066102 · Cited by 788 · see citing works
DeepCoder: Learning to Write ProgramsPreprint
Balog, M., Gaunt, A. L., Brockschmidt, M., Nowozin, S., & Tarlow, D. (2016) · International Conference on Learning Representations · doi:10.48550/arxiv.1611.01989 · Cited by 641 · see citing works
Heuristic and analytic processes in reasoning*
Evans, J. S. B. T. (1984) · British Journal of Psychology · doi:10.1111/j.2044-8295.1984.tb01915.x · Cited by 619 · see citing works
Wadler, P. L. (1990) · ACM Conference on LISP and Functional Programming (LFP) · doi:10.1145/91556.91592 · Cited by 586 · see citing works
Automating string processing in spreadsheets using input-output examples
Gulwani, S. (2011) · ACM SIGPLAN Notices · doi:10.1145/1925844.1926423 · Cited by 581 · see citing works
Synthesizing data structure transformations from input-output examples
Feser, J., Chaudhuri, S., & Dillig, I. (2015) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/2737924.2737977 · Cited by 250 · see citing works
Tate, R., Stepp, M., Tatlock, Z., & Lerner, S. (2009) · ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) · doi:10.1145/1480881.1480915 · Cited by 198 · see citing works
Program synthesis from polymorphic refinement types
Polikarpova, N., Kuraj, I., & Solar-Lezama, A. (2016) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/2908080.2908093 · Cited by 189 · see citing works
Self-citationMeta-interpretive learning of higher-order dyadic datalog: predicate invention revisited
Muggleton, S. H., Lin, D., & Tamaddoni-Nezhad, A. (2015) · Machine Learning · doi:10.1007/s10994-014-5471-y · Cited by 184 · see citing works
Synthesizing Programs for Images using Reinforced Adversarial LearningPreprint
Ganin, Y., Kulkarni, T. D., Babuschkin, I., Eslami, S. M. A., & Vinyals, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.01118 · Cited by 143 · see citing works
RobustFill: Neural Program Learning under Noisy I/OPreprint
Devlin, J., Uesato, J., Bhupatiraju, S., Singh, R., Mohamed, A., & Kohli, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.07469 · Cited by 127 · see citing works
A Machine Learning Framework for Programming by Example
Menon, A. K., Tamuz, O., Gulwani, S., Lampson, B., & Kalai, A. T. (2013) · Cited by 112 · see citing works
Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP
Muggleton, S., Schmid, U., Zeller, C., Tamaddoni‐Nezhad, A., & Besold, T. R. (2018) · Machine Learning · doi:10.1007/s10994-018-5707-3 · Cited by 108 · see citing works
Novel positional encodings to enable tree-based transformers
Shiv, V. L., & Quirk, C. (2019) · neural information processing systems · Cited by 83 · see citing works
Learning Programs: A Hierarchical Bayesian Approach
Liang, P., Jordan, M. I., & Klein, D. (2010) · Cited by 80 · see citing works
Accelerating search-based program synthesis using learned probabilistic models
Lee, W., Heo, K., Rajeev Alur, A., & Naik, M. (2018) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/3192366.3192410 · Cited by 78 · see citing works
Write, Execute, Assess: Program Synthesis with a REPL
Ellis, K., Nye, M., Pu, Y., Sosa, F., Tenenbaum, J., & Solar-Lezama, A. (2019) · arXiv · doi:10.48550/arxiv.1906.04604 · Cited by 65 · see citing works
Self-citationBeyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs
Lázaro-Gredilla, M., Lin, D., Guntupalli, J. S., & Dileep George, A. (2019) · Science Robotics · doi:10.1126/scirobotics.aav3150 · Cited by 61 · see citing works
Variational Bayesian Grammar Induction for Natural Language
Kurihara, K., & Sato, T. (2006) · Lecture notes in computer science · doi:10.1007/11872436_8 · Cited by 55 · see citing works
Bias reformulation for one-shot function induction
Dianhuan, L., Eyal, D., Kevin, E., Joshua, T., & Stephen, M. (2014) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/978-1-61499-419-0-525 · Cited by 53 · see citing works
Self-citationExecution-Guided Neural Program Synthesis.
Chen, X., Liu, C., & Song, D. X. (2018) · International Conference on Learning Representations · Cited by 52 · see citing works
Program Synthesis and Semantic Parsing with Learned Code IdiomsPreprint
Shin, E. C. R., Allamanis, M., Brockschmidt, M., & Polozov, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.10816 · Cited by 49 · see citing works
Learning to Infer Program SketchesPreprint
Nye, M., Hewitt, L., Tenenbaum, J. B., & Solar-Lezama, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.06349 · Cited by 49 · see citing works
Self-citationFlashMeta: a framework for inductive program synthesis
Polozov, O., & Gulwani, S. (2015) · ACM SIGPLAN Notices · doi:10.1145/2858965.2814310 · Cited by 48 · see citing works
HOUDINI: Lifelong Learning as Program SynthesisPreprint
Valkov, L., Chaudhari, D., Srivastava, A., Sutton, C. A., & Chaudhuri, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.00218 · Cited by 47 · see citing works
Bootstrap Learning via Modular Concept Discovery
Dechter, E., Malmaud, J., Adams, R. P., & Tenenbaum, J. B. (2014) · Cited by 43 · see citing works
Self-citationSyGuS-Comp 2017: Results and Analysis
Rajeev Alur, A., Fisman, D., Singh, R., & Solar-Lezama, A. (2017) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.260.9 · Cited by 36 · see citing works
Self-citationScientific discovery as problem solving
Simon, H. A. (1992) · International Studies in the Philosophy of Science · doi:10.1080/02698599208573403 · Cited by 35 · see citing works
Playgol: Learning Programs Through Play
Cropper, A. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/841 · Cited by 30 · see citing works
Seshia, S. A. (2012) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/2228360.2228425 · Cited by 29 · see citing works
Accelerating search-based program synthesis using learned probabilistic models
Lee, W., Heo, K., Rajeev Alur, A., & Naik, M. (2018) · ACM SIGPLAN Notices · doi:10.1145/3296979.3192410 · Cited by 28 · see citing works
Bias reformulation for one-shot function induction
Lin, D., Dechter, E., Ellis, K., Tenenbaum, J. B., & Muggleton, S. (2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 24 · see citing works
Self-citationInducing Probabilistic Programs by Bayesian Program MergingPreprint
Hwang, I., Stuhlmüller, A., & Goodman, N. D. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.5667 · Cited by 17 · see citing works
Neural Program Search: Solving Programming Tasks from Description and ExamplesPreprint
Polosukhin, I., & Skidanov, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04335 · Cited by 16 · see citing works
Library learning for neurally-guided Bayesian program induction
Ellis, K., Morales, L., Sablé-Meyer, M., Solar-Lezama, A., & Tenenbaum, J. B. (2018) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 13 · see citing works
Self-citationCumulative Learning in the Lambda Calculus
Henderson, R. (2013) · doi:10.25560/24759 · Cited by 8 · see citing works
Learning to learn generative programs with Memoised Wake-SleepPreprint
Hewitt, L., Le, T., & Tenenbaum, J. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03132 · Cited by 8 · see citing works
Self-citationLearning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context
Srivastava, S., Polozov, O., Jojić, N., & Meek, C. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.684 · Cited by 2 · see citing works
(1988) · Bulletin of Science Technology & Society · doi:10.1177/027046768800800417 · Cited by 2 · see citing works
Hancock, P. (2004) · Journal of Functional Programming · doi:10.1017/s0956796804245324 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 56 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Discovering causal relations and equations from data
Camps‐Valls, G., Gerhardus, A., Ninad, U., Varando, G., Martius, G., Balaguer‐Ballester, E., Vinuesa, R., Díaz, E., Zanna, L., & Runge, J. (2023) · Physics Reports · doi:10.1016/j.physrep.2023.10.005 · Cited by 136 · see citing works
DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning
Ellis, K., Wong, L., Nye, M., Sablé-Meyer, M., Cary, L., Anaya Pozo, L., Hewitt, L., Solar-Lezama, A., & Tenenbaum, J. B. (2023) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2022.0050 · Cited by 125 · see citing works
Self-citationReplay and compositional computation
Kurth-Nelson, Z. L., Behrens, T. E. J., Wayne, G., Miller, K. J., Luettgau, L., Dolan, R. J., Liu, Y., & Schwartenbeck, P. (2023) · Neuron · doi:10.1016/j.neuron.2022.12.028 · Cited by 93 · see citing works
A language of thought for the mental representation of geometric shapesPreprint
Sablé-Meyer, M., Ellis, K., Tenenbaum, J. B., & Dehaene, S. (2021) · Cognitive Psychology · doi:10.1016/j.cogpsych.2022.101527 · Cited by 88 · see citing works
Self-citationBuilding machines that learn and think with people
Collins, K. M., Sucholutsky, I., Bhatt, U., Chandra, K., Wong, L., Lee, M., Zhang, C. E., Zhi‐Xuan, T., Ho, M. K., Mansinghka, V. K., et al. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-01991-9 · Cited by 93 · see citing works
Self-citationCognitive Architectures for Language Agents
Sumers, T. R., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023) · arXiv · doi:10.48550/arxiv.2309.02427 · Cited by 72 · see citing works
“• Updating grounding (e.g., code-based skills; Liang et al., 2023a; Ellis et al., 2021; Wang et al., 2023a).”
BackgroundMethodHirzel, M. J. (2023) · Communications of the ACM · doi:10.1145/3587691 · Cited by 53 · see citing works
Guerrero, P., Hašan, M., Sunkavalli, K., Měch, R., Boubekeur, T., & Mitra, N. J. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530173 · Cited by 45 · see citing works
Clover: Closed-Loop Verifiable Code Generation
Sun, C., Sheng, Y., Padon, O., & Barrett, C. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-65112-0_7 · Cited by 43 · see citing works
babble: Learning Better Abstractions with E-Graphs and Anti-unification
Cao, D., Kunkel, R., Nandi, C., Willsey, M., Tatlock, Z., & Polikarpova, N. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3571207 · Cited by 38 · see citing works
Top-Down Synthesis for Library Learning
Bowers, M., Olausson, T. X., Wong, L., Grand, G., Tenenbaum, J. B., Ellis, K., & Solar-Lezama, A. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3571234 · Cited by 33 · see citing works
Self-citationSemantic programming by example with pre-trained models
Verbruggen, G., Le, V., & Gulwani, S. (2021) · Proceedings of the ACM on Programming Languages · doi:10.1145/3485477 · Cited by 26 · see citing works
Automated Program Refinement: Guide and Verify Code Large Language Model with Refinement Calculus
Cai, Y., Hóu, Z., Sanán, D., Luan, X., Lin, Y., Sun, J., & Dong, J. S. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3704905 · Cited by 27 · see citing works
The relational bottleneck as an inductive bias for efficient abstraction
Webb, T. W., Frankland, S., Altabaa, A., Segert, S., Krishnamurthy, K., Campbell, D. I., Russin, J., Giallanza, T., O’Reilly, R. C., Lafferty, J., et al. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.04.001 · Cited by 21 · see citing works
Inductive Synthesis of Structurally Recursive Functional Programs from Non-recursive Expressions
Lee, W., & Cho, H. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3571263 · Cited by 19 · see citing works
Anti-unification and Generalization: A Survey
Cerna, D. M., & Kutsia, T. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/736 · Cited by 14 · see citing works
ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipulation
Kodnongbua, M., Jones, B. T., Ahmad, M. B. S., Kim, V. G., & Schulz, A. (2023) · SIGGRAPH Asia Conference Papers · doi:10.1145/3610548.3618219 · Cited by 13 · see citing works
Peano: learning formal mathematical reasoning
Poesia, G., & Goodman, N. D. (2023) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2022.0044 · Cited by 13 · see citing works
Explainable Program Synthesis by Localizing Specifications
Nazari, A., Huang, Y., Samanta, R., Radhakrishna, A., & Raghothaman, M. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3622874 · Cited by 13 · see citing works
(2024) · doi:10.1109/icra57147.2024.10611448 · Cited by 12 · see citing works
How Do People Generalize Causal Relations over Objects? A Non-parametric Bayesian Account
Zhao, B., Lucas, C. G., & Bramley, N. R. (2021) · Computational Brain & Behavior · doi:10.1007/s42113-021-00124-z · Cited by 12 · see citing works
Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning
Kumar, S., Dasgupta, I., Daw, N. D., Cohen, J. D., & Griffiths, T. L. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011316 · Cited by 11 · see citing works
Editing Motion Graphics Video via Motion Vectorization and Transformation
Zhang, S., Ma, J., Wu, J., Ritchie, D., & Agrawala, M. (2023) · ACM Transactions on Graphics · doi:10.1145/3618316 · Cited by 12 · see citing works
Local Search and the Evolution of World Models
Bramley, N. R., Zhao, B., Quillien, T., & Lucas, C. G. (2023) · Topics in Cognitive Science · doi:10.1111/tops.12703 · Cited by 10 · see citing works
Compositional diversity in visual concept learning
Zhou, Y., Feinman, R., & Lake, B. M. (2024) · Cognition · doi:10.1016/j.cognition.2023.105711 · Cited by 10 · see citing works
Challenges and Paths Towards AI for Software EngineeringPreprint
Gu, A., Jain, N., Li, W., Shetty, M., Shao, Y., Li, Z., Yang, D., Ellis, K., Sen, K., & Solar-Lezama, A. (2025) · Qeios · doi:10.32388/vv1661 · Cited by 24 · see citing works
Self-citationAdaptive compression as a unifying framework for episodic and semantic memory
Nagy, D., Orbán, G., & Wu, C. M. (2025) · Nature Reviews Psychology · doi:10.1038/s44159-025-00458-6 · Cited by 11 · see citing works
System 0/1/2/3: Quad-Process Theory for Multitimescale Embodied Collective Cognitive Systems
Taniguchi, T., Hirai, Y., Suzuki, M., Murata, S., Horii, T., & Tanaka, K. (2025) · Artificial Life · doi:10.1162/artl.a.12 · Cited by 15 · see citing works
Scaling Neural Program Synthesis with Distribution-Based Search
Fijalkow, N., Lagarde, G., Matricon, T., Ellis, K., Ohlmann, P., & Potta, A. N. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20616 · Cited by 8 · see citing works
Self-citationProgrammatic Reward Design by Example
Zhou, W., & Li, W. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20910 · Cited by 10 · see citing works
Machine Learning and Information Theory Concepts towards an AI Mathematician
Bengio, Y., & Malkin, N. (2024) · Bulletin of the American Mathematical Society · doi:10.1090/bull/1839 · Cited by 8 · see citing works
Exploring the hierarchical structure of human plans via program generation
Correa, C. G., Sanborn, S., Ho, M. K., Callaway, F., Daw, N. D., & Griffiths, T. L. (2024) · Cognition · doi:10.1016/j.cognition.2024.105990 · Cited by 8 · see citing works
Why functional program synthesis matters (in the realm of genetic programming)
Garrow, F., Lones, M. A., & Stewart, R. (2022) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3520304.3534045 · Cited by 8 · see citing works
Zheng, X., Li, Z., Ruchkin, I., Piskač, R., & Pajić, M. (2025) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/3696630.3728500 · Cited by 7 · see citing works
Program Synthesis Guided Reinforcement LearningPreprint
Yang, Y., Inala, J. P., Bastani, O., Pu, Y., Solar-Lezama, A., & Rinard, M. (2021) · arXiv (Cornell University) · Cited by 7 · see citing works
Self-citationInductive Program Synthesis Guided by Observational Program Similarity
Feser, J., Dillig, I., & Solar-Lezama, A. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3622830 · Cited by 6 · see citing works
Self-citationLearning Paradigms for Hybrid Decision-Making Systems
Punzi, C., Pellungrini, R., Setzu, M., Giannotti, F., & Pedreschi, D. (2026) · ACM Computing Surveys · doi:10.1145/3802522 · Cited by 11 · see citing works
Bootstrapping Cognitive Agents with a Large Language Model
Zhu, F., & Simmons, R. G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i1.27822 · Cited by 6 · see citing works
CombTransformers: Statement-Wise Transformers for Statement-Wise Representations
Bertolotti, F., & Cazzola, W. (2023) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2023.3310793 · Cited by 6 · see citing works
Program Synthesis Guided Reinforcement Learning for Partially Observed EnvironmentsPreprint
Yang, Y., Inala, J. P., Bastani, O., Pu, Y., Solar-Lezama, A., & Rinard, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11137 · Cited by 6 · see citing works
Self-citationDarwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Zhang, J., Hu, S., Lu, C., Lange, R., & Clune, J. (2025) · arXiv · doi:10.48550/arxiv.2505.22954 · Cited by 5 · see citing works
Quantifying artificial intelligence through algorithmic generalization
Ito, T., Campbell, M. S., Lior Horesh, C., Klinger, T., & Ram, P. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01092-w · Cited by 6 · see citing works
Discovering quantum circuit components with program synthesis
Sarra, L., Ellis, K., & Marquardt, F. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad4252 · Cited by 6 · see citing works
Self-citationLearning Program Synthesis for Integer Sequences from Scratch
Gauthier, T., & Urban, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25930 · Cited by 5 · see citing works
GLUECons: A Generic Benchmark for Learning under Constraints
Faghihi, H. R., Nafar, A., Chen, Z., Mirzaee, R., Zhang, Y., Uszok, A., Wan, A., Premsri, T., Roth, D., & Kordjamshidi, P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26143 · Cited by 5 · see citing works
Model-Agnostic Syntactical Information for Pre-Trained Programming Language Models
Saberi, I., & Fard, F. H. (2023) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr59073.2023.00036 · Cited by 6 · see citing works
Kang, J., Jia, W., & He, X. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126882 · Cited by 4 · see citing works
Tackling the Abstraction and Reasoning Corpus (ARC) with Object-Centric Models and the MDL Principle
Ferré, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-58547-0_1 · Cited by 4 · see citing works
Combining Functional and Automata Synthesis to Discover Causal Reactive Programs
Das, R., Tenenbaum, J. B., Solar-Lezama, A., & Tavares, Z. (2023) · Proceedings of the ACM on Programming Languages · doi:10.1145/3571249 · Cited by 4 · see citing works
Self-citationProgramming by Example Made Easy
Wu, J., Wei, L., Jiang, Y., Cheung, S.-C., Ren, L., & Xu, C. (2023) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3607185 · Cited by 4 · see citing works
Improving Unsupervised Visual Program Inference with Code Rewriting Families
Ganeshan, A., Jones, R. K., & Ritchie, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01447 · Cited by 4 · see citing works
Powering up causal generalization: A model of human conceptual bootstrapping with adaptor grammarsPreprint
Zhao, B., Bramley, N. R., & Lucas, C. G. (2022) · doi:10.31234/osf.io/7gvx9 · Cited by 4 · see citing works
Insights into cognitive mechanics from education, developmental psychology and cognitive science
Hartshorne, J. K., & Jing, M. (2025) · Nature Reviews Psychology · doi:10.1038/s44159-025-00412-6 · Cited by 4 · see citing works
Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies
Shi, J., He, J., Yang, Z., Žikelić, Đ., & Lo, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3773034 · Cited by 3 · see citing works
Eberhardinger, M., Maucher, J., & Maghsudi, S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27516 · Cited by 3 · see citing works
CodeS : Natural Language to Code Repository via Multi-Layer Sketch
Zan, D., Yu, A., Liu, W., Chen, D., Shen, B., Yao, Y., Li, W., Chen, X., Gong, Y., Guan, B., et al. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3768577 · Cited by 15 · see citing works
Gauthier, T., Olšák, M., & Urban, J. (2023) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2023.109009 · Cited by 3 · see citing works
Composition of relational features with an application to explaining black-box predictors
Srinivasan, A., Baskar, A., Dash, T., & Shah, D. (2023) · Machine Learning · doi:10.1007/s10994-023-06399-6 · Cited by 3 · see citing works
AdvFusion: Adapter-based Knowledge Transfer for Code Summarization on Code Language Models
Saberi, I., Esmaeili, A., Fard, F. H., & Chen, F. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00059 · Cited by 9 · see citing works
Learning programs with magic values
Hocquette, C., & Cropper, A. (2023) · Machine Learning · doi:10.1007/s10994-022-06274-w · Cited by 3 · see citing works
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
Zelikman, E., Lorch, E., Mackey, L., & Kalai, A. T. (2023) · arXiv · doi:10.48550/arxiv.2310.02304 · Cited by 4 · see citing works
FEDT: Supporting experiment design and execution in HCI fabrication research
Savage, V., Goldstein, H., Püsök, N., Ren, J. Y., Dutt, B., Nandi, C., & Oehlberg, L. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747739 · Cited by 2 · see citing works
ODEL: An Experience-Augmented Self-Evolving Framework for Efficient Python-to-C++ Code Translation
Feng, K., Peng, F., & Wu, J. (2026) · Applied Sciences · doi:10.3390/app16031506 · Cited by 2 · see citing works
Tikzero: Zero-Shot Text-Guided Graphics Program Synthesis
Belouadi, J., Ilg, E., Keuper, M., Tanaka, H., Utiyama, M., Dabre, R., Eger, S., & Ponzetto, S. P. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01653 · Cited by 3 · see citing works
(Re)discovering Laws of Music Theory Using Information Lattice Learning
Yu, H., Varshney, L. R., Taube, H., & Evans, J. A. (2022) · IEEE BITS the Information Theory Magazine · doi:10.1109/mbits.2022.3205288 · Cited by 2 · see citing works
Equivalence by Canonicalization for Synthesis-Backed Refactoring
Lubin, J. P., Ferguson, J., Ye, K., Yim, J., & Chasins, S. (2024) · Proceedings of the ACM on Programming Languages · doi:10.1145/3656453 · Cited by 2 · see citing works
Bednarek, J., & Krawiec, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71167-1_21 · Cited by 2 · see citing works
Generating Function Names to Improve Comprehension of Synthesized Programs
Nazari, A., Swayamdipta, S., Chattopadhyay, S., & Raghothaman, M. (2024) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc60511.2024.00035 · Cited by 2 · see citing works
A language model of problem solving in humans and macaque monkeys
Yang, Q., Zhu, Z., Si, R., Li, Y., Zhang, J., & Yang, T. (2024) · Current Biology · doi:10.1016/j.cub.2024.10.074 · Cited by 2 · see citing works
Theories of Mind as Languages of Thought for Thought about ThoughtPreprint
Chandra, K., Ragan‐Kelley, J., & Tenenbaum, J. B. (2025) · doi:10.31234/osf.io/qhc6y_v1 · Cited by 2 · see citing works
Self-citationLearning Conjecturing from Scratch
Gauthier, T., & Urban, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-99984-0_23 · Cited by 1 · see citing works
Inductive synthesis of structurally recursive functional programs from non-recursive expressions
Cho, H., & Lee, W. (2025) · Journal of Functional Programming · doi:10.1017/s0956796825100063 · Cited by 1 · see citing works
Automated Discovery of Tactic Libraries for Interactive Theorem Proving
Xin, Y., Xin, J., Poesia, G., Goodman, N. D., Chen, Q., & Dillig, I. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3763121 · Cited by 1 · see citing works
Accelerating Syntax-Guided Program Synthesis by Optimizing Domain-Specific Languages
Ye, Z., Ji, R., Xiong, Y., & Zhang, X. (2026) · Proceedings of the ACM on Programming Languages · doi:10.1145/3776679 · Cited by 1 · see citing works
Zhang, Y., Bi, W., Miao, Y., & Yildirim, I. (2026) · Cognition · doi:10.1016/j.cognition.2026.106469 · Cited by 1 · see citing works
Conniving With Continuations: Representing Goals in a Domain‐Specific Language of Thought
Chandra, K., Saxe, R. R., Ragan‐Kelley, J., & Tenenbaum, J. B. (2026) · Topics in Cognitive Science · doi:10.1111/tops.70054 · Cited by 1 · see citing works
Self-citationJi, S., Choi, S., Ko, S., Kim, D., & Im, H. (2022) · ACM Symposium on Applied Computing · doi:10.1145/3477314.3507083 · Cited by 1 · see citing works
From perception to programs: regularize, overparameterize, and amortize
Tang, H., & Ellis, K. (2022) · doi:10.1145/3520312.3534865 · Cited by 1 · see citing works
Self-citationLearning to Synthesize Graphics Programs for Geometric Artworks
Bing, Q., Zhang, C., & Cai, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78456-9_17 · Cited by 1 · see citing works
Using Program Synthesis and Inductive Logic Programming to solve Bongard ProblemsPreprint
Sonwane, A., Chitlangia, S., Dash, T., Vig, L., Shroff, G. M., & Srinivasan, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09947 · Cited by 1 · see citing works
Abstraction Refinement-Guided Program Synthesis for Robot Learning from Demonstrations
Cui, G., Wang, Y., Mao, W., Duan, Y., & Zhu, H. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3763070 · Cited by 1 · see citing works
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
Naik, A., Mathur, Y., Prakam, Rose, C., & Mortensen, D. (2026) · arXiv · doi:10.48550/arxiv.2605.05485
“DreamCoder [Ellis et al., 2021] is the canonical precursor, jointly learning reusable symbolic abstractions and a neural search policy through wake-sleep library learning.”
Building Object-based Causal Programs for Human-like GeneralizationPreprint
Zhao, B., Lucas, C. G., & Bramley, N. R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12560
DeepSynth: Scaling Neural Program Synthesis with Distribution-based Search
Matricon, T., Fijalkow, N., Lagarde, G., & Ellis, K. (2022) · The Journal of Open Source Software · doi:10.21105/joss.04151
Self-citationDeterministic Graph-Walking Program Mining
Belcak, P., & Wattenhofer, R. P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-22064-7_33
WikiCoder: Learning to Write Knowledge-Powered Code
Matricon, T., Fijalkow, N., & Margueritte, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-32157-3_7
Virtual Domain Specific Languages via Embedded Projectional Editing
Korz, N., & Andrzejak, A. (2023) · ACM SIGPLAN International Conference on Generative Programming: Concepts and Experiences (GPCE) · doi:10.1145/3624007.3624059
Singh, H., Garg, P., Gupta, M., Shah, K., Goswami, A., Modi, S. K., Mondal, A. K., Khandelwal, D., Garg, D. K., & Singla, P. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.181
Constructing Deep Concepts through Shallow Search
Zhao, B., Lucas, C. G., & Bramley, N. R. (2024) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v3i1.31292
NomNom: Explanatory Function Names for Program Synthesizers
Nazari, A., Chattopadhyay, S., Swayamdipta, S., & Raghothaman, M. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3639478.3643529
Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming
Eberhardinger, M., Rupp, F., Maucher, J., & Maghsudi, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7181-3_28
HorNets: Learning from Discrete and Continuous Signals with Routing Neural NetworksPreprint
Koloski, B., Nada Lavrač, A., & Škrlj, B. (2025) · Qeios · doi:10.32388/22i1po
HorNets: learning from discrete and continuous signals with routing neural networks
Koloski, B., Nada Lavrač, A., & Škrlj, B. (2025) · Machine Learning · doi:10.1007/s10994-024-06673-1
The End of Radical Concept NativismPreprint
Rule, J., & Piantadosi, S. T. (2025) · doi:10.31234/osf.io/zs9f6_v1
Evaluation Methods for Intelligent Synthesis Technology of Aerospace Control Software
Wang, H., Ming, Z. H. A. O., Dong, X., Gu, B., Li, X., & Zhong, R. (2025) · Chinese Journal of Space Science · doi:10.11728/cjss2025.03.2024-0041
Lu, S., & Bodík, R. (2025) · Proceedings of the ACM on Programming Languages · doi:10.1145/3763162
Chen, J., Wu, J., Gao, C., Huang, Z. R., Zhong, Z., & Gan, Q. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228059
Denoised generative fusion networks for noise-robust few-shot image classification
Wu, J., Chen, J., Luo, J., Yu, W., Hu, J., & Li, H. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02178-z
Solving Abstract Reasoning Problems With Neurosymbolic Program Synthesis and Task Generation
Bednarek, J., & Krawiec, K. (2026) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732261419309
Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming
Surana, S., Srinivasan, A., & Bain, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28110-4_14
- Authors
- Ellis, K., Wong, C., Nye, M., Sablé-Meyer, M., Morales, L., Hewitt, L., Cary, L., Solar-Lezama, A., & Tenenbaum, J. B.
- Affiliations
- Cornell University (US)
- Massachusetts Institute of Technology (US)
- Collège de France (FR)
- ORCID
- Venue
- Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation
- Publisher
- ACM
- Published
- 2021-06-18
- Pages
- 835-850
- ISSN
- 1531-7102 (ISSN-L)
- OpenAlex
- W3174357804
- Cited by
- 103
- References
- 56
- Citations by year
- 2026: 14 · 2025: 24 · 2024: 18 · 2023: 30 · 2022: 10 · 2021: 7
- FWCI
- 7.51
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (publishedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- Funders
- National Science Foundation (1918839 and 1231216)
- Air Force Office of Scientific Research (FA9550-16-1-0012)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Keywords
- inductive program synthesis, bootstrapping, refactoring, program abstraction, planning, inverse graphics, equation discovery
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
