mlsanityData to 7 Oct 2026

Write, Execute, Assess: Program Synthesis with a REPL

arXiv 1906.04604 ↗First posted 9 Jun 2019cs.PL cs.AI cs.LGcited by 92

Not on the map. Why?

Abstract (arXiv)

We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search process with an interpreter or a read-eval-print-loop (REPL), which immediately executes partially written programs, exposing their semantics. The REPL addresses a basic challenge of program synthesis: tiny changes in syntax can lead to huge changes in semantics. We train a pair of models, a policy that proposes the new piece of code to write, and a value function that assesses the prospects of the code written so-far. At test time we can combine these models with a Sequential Monte Carlo algorithm. We apply our approach to two domains: synthesizing text editing programs and inferring 2D and 3D graphics programs.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 18; 2023: 22; 2024: 19; 2025: 14; 2026: 4.

92 papers.

Sort:

By area:

  1. 2021Program Synthesis with Large Language Modelscited by 3,509
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  3. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  4. 2022CodeT: Code Generation with Generated Testscited by 369
  5. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
  6. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  7. 2023Planning with Large Language Models for Code Generationcited by 179
  8. 2022SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebookscited by 121
  9. 2023GenSim: Generating Robotic Simulation Tasks via Large Language Modelscited by 120
  10. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  11. 2024BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometrycited by 101
  12. 2023Execution-based Code Generation using Deep Reinforcement Learningcited by 95
38 more
  1. 2023Hierarchical Neural Coding for Controllable CAD Model Generationcited by 84
  2. 2022SolidGen: An Autoregressive Model for Direct B-rep Synthesiscited by 78
  3. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  4. 2022Language Models Can Teach Themselves to Program Bettercited by 75
  5. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 74
  6. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
  7. 2021SketchGen: Generating Constrained CAD Sketchescited by 68
  8. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  9. 2021Engineering Sketch Generation for Computer-Aided Designcited by 49
  10. 2022Reasoning Like Program Executorscited by 45
  11. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  12. 2022Reconstructing editable prismatic CAD from rounded voxel modelscited by 41
  13. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  14. 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutionscited by 38
  15. 2021Communicating Natural Programs to Humans and Machinescited by 35
  16. 2021Latent Execution for Neural Program Synthesiscited by 35
  17. 2022Fault-Aware Neural Code Rankerscited by 33
  18. 2024Can Large Language Models Understand Symbolic Graphics Programs?cited by 32
  19. 2025HoLa: B-Rep Generation using a Holistic Latent Representationcited by 29
  20. 2024Is Programming by Example solved by LLMs?cited by 27
  21. 2021Neural-guided, Bidirectional Program Search for Abstraction and Reasoningcited by 23
  22. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 22
  23. 2025TikZero: Zero-Shot Text-Guided Graphics Program Synthesiscited by 21
  24. 2025DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometrycited by 20
  25. 2022CrossBeam: Learning to Search in Bottom-Up Program Synthesiscited by 18
  26. 2024Pix2Code: Learning to Compose Neural Visual Concepts as Programscited by 18
  27. 2023ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesiscited by 17
  28. 2023B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesiscited by 16
  29. 2025AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometrycited by 16
  30. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learningcited by 14
  31. 2025BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patchcited by 12
  32. 2022Discovering Design Concepts for CAD Sketchescited by 10
  33. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  34. 2024Diffusion On Syntax Trees For Program Synthesiscited by 10
  35. 2025VLMaterial: Procedural Material Generation with Large Vision-Language Modelscited by 9
  36. 2021Learning to Combine Per-Example Solutions for Neural Program Synthesiscited by 8
  37. 2022From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Taskscited by 8
  38. 2023Synthesis of Mathematical programs from Natural Language Specificationscited by 8

50 most cited of 92 All 92 (JSON)