Research

Resources

Support for Open AGI Progress

This page collects papers, videos, tools, codebases, and tutorials for the ARC Prize community.

Start Here

If you're just getting started with ARC-AGI, ARC Prize, or Chollet's work, we recommend you start with the following resources.

On the Measure of Intelligence (Paper) - 2019-11 - François Chollet
Francois Chollet with Dwarkesh Patel (Video) - "LLMs won't lead to AGI - $1,000,000 Prize to find true solution"
Mike Knoop with Elad Gil and Sarah Guo (Video) - "No Priors Ep. 68 With Zapier Co-Founder and Head of AI Mike Knoop"
ARC-AGI Benchmark Origins (Video) - Francois Chollet on how ARC-AGI was started
ARC-AGI-2 Technical Report (Paper) - Overview of the rationale and creation of ARC-AGI-2

Have a resource to add? Submit it.

Understanding Intelligence & ARC-AGI

Foundational theory, what ARC-AGI is, why it matters, and how we measure intelligence.

Papers

On the Measure of Intelligence - 2019-11 - François Chollet
Abstraction and analogy in AI - 2023-04 - Melanie Mitchell
Abstraction and analogy-making in artificial intelligence - 2021-06 - Melanie Mitchell
A review of emerging research directions in Abstract Visual Reasoning - 2023-03 - Mikołaj Małkiński, Jacek Mańdziuk
Neural networks for abstraction and reasoning: Towards broad generalization in machines - 2024-02 - Mikel Bober-Irizar, Soumya Banerjee
The Measure of Intelligence: Abstract and Reasoning - 2021-07 - Kshitiz Malhotra
Intelligence Analysis of Language Models - 2024-07 - Liane Galanti, Ethan Baron
Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay - 2024-07 - Gonçalo Hora de Carvalho, Oscar Knap, Robert Pollice
Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks - 2023-12 - Melanie Mitchell, Alessandro B. Palmarini, Arseny Moskvichev
The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain - 2023-05 - Arseny Moskvichev, Victor Vikram Odouard, Melanie Mitchell
Evaluating Understanding on Conceptual Abstraction Benchmarks - 2022-06 - Victor Vikram Odouard, Melanie Mitchell
Do Large Language Models Solve ARC Visual Analogies Like People Do? - 2024-05 - Gustaw Opiełka, Hannes Rosenbusch, Veerle Vijverberg, Claire E. Stevenson
Fast and flexible: Human program induction in abstract reasoning tasks - 2021-03 - Aysja Johnson, Wai Keen Vong, Brenden M. Lake, Todd M. Gureckis
Core knowledge objects in reasoning and language use for highly abstract inductive tasks - 2021-07 - Gabrielle Ecanow, Catherine Wong, Sam Acquaviva, Yewen Pu, Marta Kryven, Josh Tenenbaum
PQA: Perceptual Question Answering - 2021-04 - Yonggang Qi, Kai Zhang, Aneeshan Sain, Yi-Zhe Song

Videos & Talks

François Chollet: Measures of Intelligence - Lex Fridman Podcast #120 [ARC from 1:35:59] (2020-08-30)
#51 FRANCOIS CHOLLET - Intelligence and Generalisation (2021-04-16)
Francois Chollet - Why abstraction is the key to intelligence, and what we're still missing (2021-09-22)
Francois Chollet - On the Measure Of Intelligence (2020-06-18)
Francois Chollet: What is the future of artificial intelligence? (2020-06-15)
François Chollet on Deep Learning and the Meaning of Intelligence (2024-06-24)
The Gradient Podcast - François Chollet: Keras and Measures of Intelligence (2024-01-12)
François Chollet - Creating Keras 3 (2024-04-18)
ARC challenge is a hard test for machines, easy for humans - François Chollet and Lex Fridman (2020-09-03)
AI BENCHMARKS ARE BROKEN! [Prof. MELANIE MITCHELL] (2023-09-10)
Abstraction and Analogy are the Keys to Robust AI - Melanie Mitchell (2022-08-05)
Melanie Mitchell - Abstraction and Analogy in Artificial Intelligence - IPAM at UCLA (2022-02-15)
The Gradient Podcast - Melanie Mitchell: Abstraction and Analogy in AI (2024-01-11)
The Future of Artificial Intelligence (2024-02-22)
Are Neural Networks Intelligent? (2020-12-07)
The Debate Over "Understanding" in AI's Large Language Models [ARC from 33:45] (2024-04-22)
EP 217 Ben Goertzel on a New Framework for AGI (2024-01-24)
The IQ of AI: Measuring Intelligence in AI Models (2023-11-16)
ChatGPT Shatters the Turing Test: A New Era Dawns in AI Conversation! (2023-08-16)
What is ARC (Abstraction and Reasoning Corpus) (2023-05-27)
How do humans solve ARC tasks, Abstraction & Reasoning Corpus (2024-04-21)
A Glimpse of the Happy ARC Day (2022-08-03)
why AI can't pass this test (2023-08-31)
The Simple $1,000,000 Problem AI Can't Solve (2024-06-13)
AI Won't Be AGI, Until It Can At Least Do This (plus 6 key ways LLMs are being upgraded) (2024-06-17)
ARC PRIZE - Win $1Million to Beat the ARC-AGI benchmark (2024-06-18)
Chollet's ARC Challenge + Current Winners (2024-06-18)
Googlers React To Dwarkesh Patel & Francois Chollet - ARC Challenge On Path To Be Beaten (2024-06-22)
This puzzle is easy for humans but hard for AI. How quickly can you solve it? (2024-06-22)
fchollet/ARC-AGI - Gource visualisation (2024-06-14)
$1m prize for AI that can solve puzzles that are simple for humans (2024-06-25)
$1M bet ChatGPT won't lead to AGI, Apple's intelligent AI use, AI millionaires surge: AI Eye (2024-06-13)
ARC Prize 2024 (2024-06-21)

Blog Posts & Articles

Why the Abstraction and Reasoning Corpus is interesting and important for AI - Blog Post
On Evaluating Understanding and Generalization in the ARC Domain - Blog Post
ARC: Where do we stand today? - Blog Post
ARC: Core Knowledge - ARC Overview
AI Abstraction - Blog Post
AI's Next Step: Abstraction & Reasoning - Blog Post
IQ test for AI: The ARC Challenge - Blog Post
Inside Kaggle's most important AI competition - Article

Approaches to Solving ARC

Research papers, technical talks, and videos exploring methods and techniques for tackling ARC-AGI.

Papers

Channel-Wise MLPs Improve the Generalization of Recurrent Convolutional Networks - 2025-08 - Nathan Breslow
THE ROLE OF POSITIONAL ENCODINGS IN THE ARC BENCHMARK - 2025-01-31
Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL - 2024-08 - Jihwan Lee, Woochang Sim, Sejin Kim, Sundong Kim
Relational Decomposition for Program Synthesis - 2024-08 - Céline Hocquette, Andrew Cropper
Automated Design of Agentic Systems - 2024-08 - Shengran Hu, Cong Lu, Jeff Clune
Learning to (Learn at Test Time): RNNs with Expressive Hidden States - 2024-07 - Yu Sun, Xinhao Li, Karan Dalal, Jiarui Xu, Arjun Vikram, Genghan Zhang, Yann Dubois, Xinlei Chen, Xiaolong Wang, Sanmi Koyejo, Tatsunori Hashimoto, Carlos Guestrin
Hypothesis Search: Inductive Reasoning with Language Models - 2024-05 - Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
Diffusion On Syntax Trees For Program Synthesis - 2024-05 - Shreyas Kapur, Erik Jenner, Stuart Russell
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis - 2024-05 - Shraddha Barke, Emmanuel Anaya Gonzalez, Saketh Ram Kasibatla, Taylor Berg-Kirkpatrick, Nadia Polikarpova
Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus - 2024-05 - Filipe Marinho Rocha, Inês Dutra, Vítor Santos Costa
Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation - 2024-04 - Michael Hodel
Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus - 2024-03 - Seungpil Lee, Woochang Sim, Donghyeon Shin, Sanha Hwang, Wongyu Seo, Jiwon Park, Seokki Lee, Sejin Kim, Sundong Kim
Analysis of Parent with Fine Tuned Large Language Model - 2024-03 - Vaishali Baviskar, Shrinidhi Shedbalkar, Varun More, Sagar Waghmare, Yash Wafekar, Madhushi Verma
Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning - 2024-02 - Mattia Atzeni
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay - 2024-02 - Natasha Butt, Blazej Manczak, Auke Wiggers, Corrado Rainone, David Zhang, Michaël Defferrard, Taco Cohen
LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations - 2024-02 - Yudong Xu, Wenhao Li, Pashootan Vaezipoor, Scott Sanner, Elias B. Khalil
Enhancing the Building Blocks of Language-Based Visual Reasoning for ARC - 2024-01 - Benjamin Glaus
Generalized Planning for the Abstraction and Reasoning Corpus - 2024-01 - Chao Lei, Nir Lipovetzky, Krista A. Ehinger
Counting and Algorithmic Generalization with Transformers - 2024-01 - Simon Ouellette, Rolf Pfister, Hansueli Jud
Assessing GPT4-V on Structured Reasoning Tasks - 2023-12 - Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Gust Verbruggen
ANPL: Towards Natural Programming with Interactive Decomposition - 2023-11 - Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin, Shaohui Peng, Yuanbo Wen, Rui Zhang, Zidong Du, Qi Guo, Yewen Pu, Yunji Chen
Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method - 2023-11 - Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch, Claire E. Stevenson
Solving ARC with non-procedural program induction - 2023-11 - Norbert Neumann, Ádám Pintér
Tackling the Abstraction and Reasoning Corpus (ARC) with Object-centric Models and the MDL Principle - 2023-11 - Sébastien Ferré
A Neurodiversity-Inspired Solver for the Abstraction & Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis - 2023-10 - James Ainooson, Deepayan Sanyal, Joel P. Michelson, Yuan Yang, Maithilee Kunda
Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge - 2023-10 - John Chong Min Tan, Mehul Motani
Large Language Models as General Pattern Machines - 2023-10 - Suvir Mirchandani, Fei Xia, Pete Florence, Brian Ichter, Danny Driess, Montserrat Gonzalez Arenas, Kanishka Rao, Dorsa Sadigh, Andy Zeng
Hypothesis Search: Inductive Reasoning with Language Models - 2023-09 - Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
Abstract Visual Reasoning Enabled by Language - 2023-06 - Giacomo Camposampiero, Loic Houmard, Benjamin Estermann, Joël Mathys, Roger Wattenhofer
Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer - 2023-06 - Jaehyun Park, Jaegyun Im, Sanha Hwang, Mintaek Lim, Sabina Ualibekova, Sejin Kim, Sundong Kim
Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning - 2023-06 - Mattia Atzeni, Mrinmaya Sachan, Andreas Loukas
An Approach to Solving the Abstraction and Reasoning Corpus (ARC) Challenge - 2023-06 - Tan John Chong Min
Communicating Natural Programs to Humans and Machines - 2023-05 - Samuel Acquaviva, Yewen Pu, Marta Kryven, Theodoros Sechopoulos, Catherine Wong, Gabrielle E Ecanow, Maxwell Nye, Michael Henry Tessler, Joshua B. Tenenbaum
A Divide-Align-Conquer Strategy for Program Synthesis - 2023-01 - Jonas Witt, Stef Rasing, Sebastijan Dumančić, Tias Guns, Claus-Christian Carbon
Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus - 2022-12 - Yudong Xu, Elias B. Khalil, Scott Sanner
ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy - 2022-07 - Daniel Zeng, Tailin Wu, Jure Leskovec
Object-centric Compositional Imagination for Visual Abstract Reasoning - 2022-07 - Rim Assouel, Pau Rodriguez, Perouz Taslakian, David Vazquez, Yoshua Bengio
First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle - 2021-12 - Sébastien Ferré
Neural-guided, Bidirectional Program Search for Abstraction and Reasoning - 2021-10 - Simon Alford, Anshula Gandhi, Akshay Rangamani, Andrzej Banburski, Tony Wang, Sylee Dandekar, John Chin, Tomaso Poggio, Peter Chin
LARC: Language annotated Abstraction and Reasoning Corpus - 2021-07 - Sam Acquaviva, Yewen Pu, Maxwell Nye, Catherine Wong, Michael Henry Tessler, Josh Tenenbaum
A Neurosymbolic Approach to Abstraction and Reasoning - 2021-06 - Simon Alford
Neural Abstract Reasoner - 2020-11 - Victor Kolev, Bogdan Georgiev, Svetlin Penkov
Solving Abstract Reasoning Tasks with Grammatical Evolution - 2020-09 - Raphael Fischer, Matthias Jakobs, Sascha Mücke, Katharina Morik
Dreaming with ARC - 2020-07 - Andrzej Banburski, Simon Alford, Anshula Gandhi, Sylee Dandekar, Peter Chin, Tomaso Poggio

Videos & Talks

How my MoA will Win $1M ! ARC-AGI Prize (2024-06-23)
Claude 3.5 struggle too?! The $Million dollar challenge (2024-06-26)
Can GPT4 solve the Abstraction and Reasoning Corpus (ARC) Challenge Zero-Shot? (2023-04-17)
LLMs as a System of Multiple Expert Agents to solve the ARC Challenge (Detailed Walkthrough) (2023-10-10)
LLMs as a system to solve the Abstraction and Reasoning Corpus (ARC) Challenge! (2023-06-20)
LLMs as General Pattern Machines: Use Arbitrary Tokens to Pattern Match? (2023-08-15)
LLM as Pattern Machines(Part 2) - Goal Directed Decision Transformers, 10-Year Plan for Intelligence (2023-08-23)
Modular Learning and Reasoning on ARC (2021-02-11)
#97 SREEJAN KUMAR - Human Inductive Biases in Machines from Language (2023-01-28)
Learning Part-Whole Structure by Chunking - More Efficient than Deep Learning!!! (2023-02-28)
Hierarchy! The future of AI: How it helps representations and why it is important. (2023-05-25)
GPT 4: The Progress of AI, ConceptARC Challenge AI Paper Explained (2023-07-26)
ARC Challenge - IBS/KAIST Data Science Seminar Series (2022-08-11)
ARC Challenge - Using NLP Models 1 (2022-07-13)
ARTI – An ARC Challenge Solver Architecture (2022-11-02)
ARC - My approach to the ARC Challenge (2021-09-28)
Summer Intern Talk - Prin (2022-12-28)
Math Psych 2021 (ARC) (2021-06-15)
[5 min] communicating natural programs to humans and machines (2023-01-04)
Language annotated Abstraction and Reasoning Corpus (2021-07-21)
ARC (Abstraction and Reasoning Corpus) mutations printed to console (2023-07-22)

Blog Posts & Articles

ARC-AGI Without Pretraining (Isaac Liao and Albert Gu) - Tweet, Kaggle Template, Post
Test-Time Augmentation to solve ARC - Interview
The Search for Compositional Generalization - Research Post
Dataset-Induced Meta-Learning (and other tricks): Improving model efficiency on ARC - Research Post
Neural Abstract Reasoner - Posting

Tools & Playgrounds

Interactive tools, editors, and games for exploring and solving ARC-AGI puzzles.

ARC-AGI Puzzle Explorer
ARC Playground and Editor By Lab42 - Game
Welcome to Brain Grid Game! - Game
O2ARC 3.0: A Platform for Solving and Creating ARC Tasks - Game
DARC: A Recursive Decomposition Dataset of ARC Tasks - Game
ARC Game - Game
Could AI solve this puzzle? (ARC-Game) (2021-11-16)
Abstract Reasoning Corpus IDE (2021-02-12)
ARC IDE demo (2021-02-12)
ARC World: Login Page (2023-06-04)
Output size tool for ARC (Abstraction and Reasoning Corpus) (2023-06-17)
ARC eye tracking introduction (2024-02-14)
Painting with my eyes, webgazer and D3 (2023-12-31)
Playgrounds for Abstraction and Reasoning - 2022-10 - Subin Kim, Prin Phunyaphibarn, Donghyun Ahn, Sundong Kim
ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning - 2024-07 - Hosung Lee, Sejin Kim, Seungpil Lee, Sanha Hwang, Jihwan Lee, Byung-Jun Lee, Sundong Kim
O2ARC 3.0: A Platform for Solving and Creating ARC Tasks (To appear at IJCAI 2024 demo) - 2024-02 - Suyeon Shim, Dohyun Ko, Hosung Lee, Seokki Lee, Doyoon Song, Sanha Hwang, Sejin Kim and Sundong Kim

Code & Datasets

GitHub repositories with solvers, DSLs, datasets, and tools for building on ARC-AGI.

Competition Solutions & Writeups

Past competition results, solution writeups, and approaches that have performed well.

Abstraction and Reasoning Challenge (2020) - Kaggle
Icecuber - Write up behind the #1 solution in the 2020 Kaggle competition by icecuber. 20 of 100 private evaluation tasks solved
Alejandro De Miquel - 2nd place solution in 2020 competition
Ilia Larchenko - Sample of the 3rd place solution in 2020 competition
Alijs - Quick 2020 5th place notes
Zoltan - 2020 6th place write up
Hieu Phung - 2020 9th place solution write up
Alexander Fritzler - 2020 10th place solution write up
James Mcguigan - Explanation of attempts in the 2020
ARC2023 - End to End - V7 - 31 of 100 private evaluation tasks solved
Alejandro de Miquel - 2nd in ARC Kaggle Challenge - EP 03 (2020-11-17)
The Hardest Kaggle Challenge (2020-03-02)
Finishing 2nd in Kaggle's Abstraction and Reasoning Challenge - Blog Post
A Commentary on the Abstraction and Reasoning Challenge — Kaggle Competition - Blog Post

Courses & Tutorials

Structured learning content, step-by-step walkthroughs, and guided explanations for getting hands-on with ARC-AGI.

Program Synthesis and the ARC-AGI Challenge - By Fausto Carcassi - A concise introductory course by Fausto Carcassi on program synthesis fundamentals, providing foundational tools and methods to understand and approach the ARC Challenge.
On the Measure of Intelligence (Introduction) (2020-06-14)
On the Measure of Intelligence by François Chollet - Part 2: Human Priors (Paper Explained) (2020-06-19)
On the Measure of Intelligence by François Chollet - Part 3: The Math (Paper Explained) (2020-06-26)
On the Measure of Intelligence by François Chollet - Part 4: The ARC Challenge (Paper Explained) (2020-07-03)
On the Measure of Intelligence (2023-04-21)
[CW Paper-Club] On the Measure of Intelligence (2023-09-12)
SupCog EP3 - On the Measure of Intelligence, by François Chollet (2021-01-19)
AI Abstraction and Reasoning - More Human-like AI - Kaggle Competition Part 1: Overview (2020-04-10)
ARC Challenge Live Coding (2022-07-02)
Spoiler Alert! - ARC-AGI puzzle solving by real humans #ARCPrize #AGI #puzzle #iqtest (2024-06-13)
Task 0934a4d8 - Repair symmetry and crop - Abstraction and Reasoning Corpus (ARC) (2023-04-17)
Solving 4 tasks of Abstraction and Reasoning Corpus (ARC) (2024-01-16)
Solving ARC task 18419cfa (Abstraction and Reasoning Corpus) (2024-01-18)
Solving ARC 33b52de3, Abstraction & Reasoning corpus (2024-02-18)
Tracking of objects between input and output - ARC (Abstraction and Reasoning Corpus) (2023-07-16)
youtube arc solution description (2023-05-20)