mlsanityData to 7 Oct 2026

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

arXiv 2603.05099 ↗First posted 5 Mar 2026cs.CL cs.AI cs.LGcited by 1

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

The Abstraction and Reasoning Corpus (ARC-AGI) probes few-shot abstraction and rule induction on small visual grids, but progress is difficult to measure on static collections of hand-authored puzzles due to overfitting, dataset leakage, and memorisation. We introduce ARC-TGI (ARC Task Generators Inventory), an open-source framework for task-family generators: compact Python programs that sample diverse ARC-AGI tasks while preserving a latent rule. ARC-TGI is built around a solver-facing representation: each generated task is paired with natural-language input and transformation reasoning chains and partially evaluated Python code implementing sampling, transformation, and episode construction. Crucially, ARC-TGI supports task-level constraints so that training examples collectively expose the variations needed to infer the underlying rule, a requirement for human-solvable ARC tasks that independent per-example sampling often fails to guarantee. All generators undergo human refinement and local verification to keep both grids and reasoning traces natural and consistent under variation. We release 461 generators covering 180 ARC-Mini tasks, 215 ARC-AGI-1 tasks (200 train, 15 test), and 66 ARC-AGI-2 tasks (55 train, 11 test), enabling scalable dataset sampling and controlled benchmarking.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 14 of its 25 references that are in the map. First posted on arXiv 5 Mar 2026.

Builds on

14 of 25 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025GIFARC: Synthetic Dataset for Leveraging Human-Intuitive Analogies to Elevate AI Reasoning27 May

Other references · 13

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2023Mistral 7Bcited by 3,065
  3. 2024Mixtral of Expertscited by 1,785
  4. 2025Gemma 3 Technical Reportcited by 1,686
  5. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  6. 2024Phi-4 Technical Reportcited by 675
  7. 2019On the Measure of Intelligencecited by 129
  8. 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 97
  9. 2025Olmo 3cited by 95
  10. 2024H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmarkcited by 32
  11. 2024Addressing the Abstraction and Reasoning Corpus via Procedural Example Generationcited by 31
  12. 2024Towards Efficient Neurally-Guided Program Induction for ARC-AGIcited by 11
1 more
  1. 2025ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpuscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Signed Compression Progress on a Sealed Audit is Goodhart-Resistantcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute
  2. 2026Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2
  3. 2025ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving
  4. 2024Neural networks for abstraction and reasoning: Towards broad generalization in machines
  5. 2025ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
  6. 2026PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
  7. 2026A Systematic Study of Small Language Models on Abstract Reasoning Tasks
  8. 2025Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective