Overview

ARC-AGI tests whether systems can infer a task’s underlying rule from a few examples, usually by transforming colored grids in ARC-AGI-1 and ARC-AGI-2 or adapting to interactive environments in ARC-AGI-3. Approaches include program synthesis with domain-specific languages, neural transformers with test-time training, search over candidate rules, and agents that build executable world models. Systems can score highly on particular public evaluations, but performance does not reliably transfer across benchmark versions or establish robust generalization to new tasks. A central tension is how to measure genuine abstraction while guarding against shortcuts and accounting for interaction efficiency, compute cost, and the persistent gap from human performance on harder settings.

Latest papers

CardsList

31 papers11 papers in the last four weeks, up 175% on the four weeks before. 0.1% of all new papers.

  1. Interactive Program Induction with Language Model Priors

    Nov 13, 2026Robin Shing Moon Chan, Ryan CotterellInductive InferenceActive Learning

  2. Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation

    Nov 10, 2026Luca Favole, Giorgio Mongardi, Giovanni Squillero +1ARC-AGIProgram Synthesis

  3. How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

    Nov 9, 2026Ku Onoda, Haruto Kawano, Shota Takashiro +1Game World ModelsWorld Model Learning

  4. Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2

    Nov 4, 2026Nguyen Minh Thang, Trinh Thi PhuongARC-AGIFine-Tuning Language Models

  5. Algebraic World Model: From Exploration to Proofs

    Oct 29, 2026Guancheng Pan, Qixin Tan, Yang Yuan +1ARC-AGIAutomated Theorem Proving

  6. How Humans Learn Unfamiliar Worlds: A Think-Aloud Dataset on ARC-AGI-3

    Oct 25, 2026Shuzhi Liu, Archana Warrier, Dat Nguyen +3World Model LearningHuman Behavior Modeling

  7. Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3

    Oct 21, 2026Jens Lehmann, Sahar VahdatiLLM Agent HarnessesAgent Harness Optimization

  8. Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URM

    Oct 19, 2026Sara Neri, Eugenio Gaeta, Andrea Ceschini +2Recursive Reasoning ModelsAbstract Reasoning

  9. Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

    Oct 8, 2026Haoyu Zhao, Zhengxu Yu, Zhiyuan He +5Continual Learning for LLM AgentsRecursive Self-Improvement

  10. Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks

    Sep 18, 2026Adrien Deliège, Claas Beger, Marc Van Droogenbroeck +1Test-Time TrainingVisual Reasoning

  11. Scaling Discovery through Test-Time Communication

    Sep 17, 2026Jongho Park, Vasilis Kontonis, Shivam Garg +2Multi-Agent CollaborationMulti-Agent Communication

  12. Twin: Playing an Unknown Game with a Test-Time Digital Twin

    Aug 14, 2026Alexy Skoutnev, Kirill Acharya, Gaston Longhitano +3Game-Playing AgentsCode World Models

  13. BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

    Aug 10, 2026Björn Engdahl, Adrian Kosowski, Jan Chorowski +6Cost-Aware InferenceAbstract Reasoning

  14. Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

    Jul 30, 2026Jens Lehmann, Andrei Aioanei, Sahar VahdatiGame-Playing AgentsAI Coding Agents

  15. ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning

    Jul 10, 2026Kunbo Zhang, Lei Fu, Zeyu Wang +2Program SynthesisMulti-Agent Collaboration

  16. Multi-Perspective Transformers in ARC-AGI-2 Challenge

    May 1, 2026Caleb Talley, Vedant Tibrewal, Seun Adekunle +3Visual ReasoningProduct of Experts

  17. Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

    Mar 20, 2026Yu-Ning Qiu, Lin-Feng Zou, Jiong-Da Wang +2ARC-AGINeuro-Symbolic Reasoning

  18. The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning

    Mar 9, 2026Sahar Vahdati, Andrei Aioanei, Haridhra Suresh +1Abstract ReasoningARC-AGI

  19. ARC-TGI: Human-Validated Task Generators with Reasoning Chain Templates for ARC-AGI

    Mar 5, 2026Jens Lehmann, Syeda Khushbakht, Nikoo Salehfard +4ARC-AGISynthetic Data Generation