mlsanityData to 7 Oct 2026

Relational decomposition for program synthesis

arXiv 2408.12212 ↗First posted 22 Aug 2024cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce a relational approach to program synthesis. The key idea is to decompose synthesis tasks into simpler relational synthesis subtasks. Specifically, our representation decomposes a training input-output example into sets of input and output facts respectively. We then learn relations between the input and output facts. We demonstrate our approach using an off-the-shelf inductive logic programming (ILP) system on four challenging synthesis datasets. Our results show that (i) our representation can outperform a standard one, and (ii) an off-the-shelf ILP system with our representation can outperform domain-specific approaches.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 49 references that are in the map. First posted on arXiv 22 Aug 2024.

Builds on

20 of 49 references.

References · 20

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2023Large Language Models as General Pattern Machinescited by 196
  3. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
  4. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  5. 2019Write, Execute, Assess: Program Synthesis with a REPLcited by 92
  6. 2020Inductive logic programming at 30: a new introductioncited by 83
  7. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representationscited by 81
  8. 2020Learning programs by learning from failurescited by 73
  9. 2019Learning to Infer and Execute 3D Shape Programscited by 68
  10. 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoffcited by 50
  11. 2022Graphs, Constraints, and Search for the Abstraction and Reasoning Corpuscited by 32
  12. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policiescited by 30
8 more
  1. 2019Making sense of sensory inputcited by 29
  2. 2017One Model for the Learning of Languagecited by 21
  3. 2022CrossBeam: Learning to Search in Bottom-Up Program Synthesiscited by 18
  4. 2021Discovering State and Action Abstractions for Generalized Task and Motion Planningcited by 17
  5. 2024Generalized Planning for the Abstraction and Reasoning Corpuscited by 10
  6. 2022Learning logic programs by combining programscited by 7
  7. 2023A Divide-Align-Conquer Strategy for Program Synthesiscited by 7
  8. 2023Program Synthesis with Best-First Bottom-Up Searchcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Combining Induction and Transduction for Abstract Reasoningcited by 53
  2. 2024Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objectscited by 9
  3. 2025Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Modelcited by 2
  4. 2025Vector Symbolic Algebras for the Abstraction and Reasoning Corpuscited by 1
  5. 2025An Empirical Comparison of Cost Functions in Inductive Logic Programmingcited by 0
  6. 2026From Global to Factor-Wise Expert Composition in Discrete Diffusion Modelscited by 0