mlsanityData to 14 Oct 2026

An Approach to Solving the Abstraction and Reasoning Corpus (ARC) Challenge

arXiv 2306.03553 ↗First posted 6 Jun 2023cs.AIcited by 3

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

We utilise the power of Large Language Models (LLMs), in particular GPT4, to be prompt engineered into performing an arbitrary task. Here, we give the model some human priors via text, along with some typical procedures for solving the ARC tasks, and ask it to generate the i) broad description of the input-output relation, ii) detailed steps of the input-output mapping, iii) use the detailed steps to perform manipulation on the test input and derive the test output. The current GPT3.5/GPT4 prompt solves 2 out of 4 tested small ARC challenges (those with small grids of 8x8 and below). With tweaks to the prompt to make it more specific for the use case, it can solve more. We posit that when scaled to a multi-agent system with usage of past memory and equipped with an image interpretation tool via Visual Question Answering, we may actually be able to solve the majority of the ARC challenge

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 16 of its 26 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

16 of 26 references.

References · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  10. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  11. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  12. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
4 more
  1. 2021How Many Data Points is a Prompt Worth?cited by 198
  2. 2016Visual Question Answering: A Survey of Methods and Datasetscited by 123
  3. 2023Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environmentscited by 3
  4. 2022Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environmentscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challengecited by 11
  2. 2025Understanding LLMs' Fluid Intelligence Deficiency: An Analysis of the ARC Taskcited by 4
  3. 2025From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmarkcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations
  2. 2025ARC Is a Vision Problem!
  3. 2023Abstract Visual Reasoning Enabled by Language
  4. 2025Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
  5. 2024Intelligence Analysis of Language Models
  6. 2024Do Large Language Models Solve ARC Visual Analogies Like People Do?
  7. 2024Neural networks for abstraction and reasoning: Towards broad generalization in machines
  8. 2026DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models