mlsanityData to 14 Oct 2026

Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer

arXiv 2306.08204 ↗First posted 14 Jun 2023cs.AI cs.LGcited by 12

On the map: Offline RL and imitation learning from data → Decision transformers and sequence modeling

Abstract (arXiv)

In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human problem-solving, and introduce an object detection algorithm, the Push and Pull clustering method. This dual strategy enhances AI's ARC problem-solving skills and provides insights for AGI progression. Yet, our work reveals the need for advanced data collection tools, robust training datasets, and refined model structures. This study highlights potential improvements for Decision Transformers and propels future AGI research.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data. Builds on 22 of its 31 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

22 of 31 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Prompting Decision Transformer for Few-Shot Policy Generalization27 Jun
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modeling2 Jun

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  9. 2020Object-Centric Learning with Slot Attentioncited by 876
  10. 2018Behavioral Cloning from Observationcited by 492
  11. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  12. 2023A Categorical Archive of ChatGPT Failurescited by 168
8 more
  1. 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 101
  2. 2020Learning Compositional Rules via Neural Program Synthesiscited by 74
  3. 2022Transformers are Meta-Reinforcement Learnerscited by 41
  4. 2021Communicating Natural Programs to Humans and Machinescited by 35
  5. 2021Fast and flexible: Human program induction in abstract reasoning taskscited by 33
  6. 2022Graphs, Constraints, and Search for the Abstraction and Reasoning Corpuscited by 32
  7. 2018Global overview of Imitation Learningcited by 16
  8. 2022Evaluating Understanding on Conceptual Abstraction Benchmarkscited by 13

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 8; 2025: 3.

12 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2025ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
  2. 2025ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving
  3. 2024Neural networks for abstraction and reasoning: Towards broad generalization in machines
  4. 2025ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
  5. 2023Abstract Visual Reasoning Enabled by Language
  6. 2026ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI
  7. 2025ARC Is a Vision Problem!
  8. 2026Reasoning is a Modality