mlsanityData to 7 Oct 2026

Towards Efficient Neurally-Guided Program Induction for ARC-AGI

arXiv 2411.17708 ↗First posted 13 Nov 2024cs.AI cs.CL cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

ARC-AGI is an open-world problem domain in which the ability to generalize out-of-distribution is a crucial quality. Under the program induction paradigm, we present a series of experiments that reveal the efficiency and generalization characteristics of various neurally-guided program induction approaches. The three paradigms we consider are Learning the grid space, Learning the program space, and Learning the transform space. We implement and experiment thoroughly on the first two, and retain the second one for ARC-AGI submission. After identifying the strengths and weaknesses of both of these approaches, we suggest the third as a potential solution, and run preliminary experiments.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 5 of its 43 references that are in the map. First posted on arXiv 13 Nov 2024.

Builds on

5 of 43 references.

References · 5

  1. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
  2. 2021Latent Execution for Neural Program Synthesiscited by 35
  3. 2020Representing Partial Programs with Blended Abstract Semanticscited by 14
  4. 2024Diffusion On Syntax Trees For Program Synthesiscited by 10
  5. 2021Scaling Neural Program Synthesis with Distribution-based Searchcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 5.

11 papers.

  1. 2024ARC Prize 2024: Technical Reportcited by 103
  2. 2025ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpuscited by 8
  3. 2026The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoningcited by 4
  4. 2025Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuningcited by 2
  5. 2026Slots, Transitions, Loops: Learning Composable World Models for ARCcited by 2
  6. 2025Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalizationcited by 1
  7. 2025Vector Symbolic Algebras for the Abstraction and Reasoning Corpuscited by 1
  8. 2025ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solvingcited by 1
  9. 2026ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGIcited by 1
  10. 2026TraceViT: Grounded Trace Supervision for Visual Abstract Reasoningcited by 1
  11. 2026On the Exact Algorithmic Extraction of Finite Tesselations Through Prime Extraction of Minimal Representative Formscited by 0