cs.CLMar 5, 2026

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

Authors: Jens Lehmann, Syeda Khushbakht, Nikoo Salehfard, Nur A Zarin Nishat, Dhananjay Bhandiwad, Andrei Aioanei, Sahar Vahdati

Organizations: Dresden University of Technology Dresden, Germany · Amazon · TIB - Leibniz Information Centre Hanover, Germany · TIB - Leibniz Information Centre Leibniz University of Hanover Hanover, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

MethodRole (fixed signature)
create_input(self, taskvars: dict, gridvars: dict) -> np.ndarray : sample an input grid while randomizing nuisance factors.
transform_input(self, grid: np.ndarray, taskvars: dict) -> np.ndarray : deterministically apply the latent rule to produce the output grid.
create_grids(self) -> Tuple[Dict[str, Any], TrainTestData] : construct a complete episode (train/test pairs) and return sampled variables plus train/test data.
Table 1. ARC-TGI generator API. taskvars are per-episode variables used to instantiate templates; gridvars are per-grid auxiliaries used during sampling.
Figure 1. Input grid-size heatmaps. Upper row: original tasks. Lower row: ARC-TGI samples (50 per generator).
Figure 2. ARC-AGI task (Task ID: e509e548) and corresponding ARC-TGI sample.
Figure 3. Per-grid diversity visualization for one ARC-TGI generator ( taskcmBhVbGzL8ZgWXDE5CUS6B ), showing variation in spatial position, size, and color across sampled grids while preserving the latent rule.
Figure 4. Few-shot performance on ARC-TGI-50N . (A) ARC-style episode: infer a latent rule from training input/output pairs and apply it to a test input. (B) Exact-match accuracy across models on ARC-TGI-50N .
Figure 5. Per-generator performance across models (200 generators). Heatmap of model accuracy by generator. Models are ordered by mean accuracy (y-axis) and generators are ordered by Qwen3-30B accuracy (x-axis), revealing shared easy/hard regions and sparse success on the hardest generators.
Figure 6. Per-generator accuracy for Qwen3-30B. Accuracy over generators (50 samples per generator), highlighting broad coverage with a long-tail of difficult task families.
Figure 7. Per-generator comparison: Qwen3-30B vs. Claude Sonnet 4.5. Each point summarizes accuracy on a generator (50 samples), showing largely consistent generator difficulty with occasional reversals.
Figure 8. Core-knowledge priors vs. accuracy. Distribution of dominant priors across accuracy bins for Qwen3-30B and Sonnet 4.5 (manual annotation on stratified samples).
Figure 9. Post-fine-tuning task coverage across 200 generators. Stacked bars summarize task-level accuracy across generators after fine-tuning on ARC-TGI-50N .
Figure 10. Fine-tuning effects on ID vs. OOD evaluation. Accuracy for pre-trained models on ARC-TGI (PT-ARC-TGI), after ARC-TGI fine-tuning evaluated ID (FT-ARC-TGI ID) and on ARC-AGI-1 eval (FT-ARC-TGI OOD), and after fine-tuning on ARC-AGI-1 train evaluated on ARC-AGI-1 eval (FT-ARC-AGI-1 OOD).
Figure 11. Per-generator change after ARC-TGI fine-tuning. Number of generators whose accuracy improves, declines, or remains unchanged (per model).
Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 12. Within family task generalisation
Figure 13. Train–test consistency
Figure 14. ARC-AGI task (Task ID: 103eff5b) and corresponding ARC-TGI sample.
Figure 16
More in this topic

ARC-AGI

ARC-AGI (Abstraction and Reasoning Corpus for Artificial General Intelligence) benchmarks the ability to infer and apply abstract rules from sparse examples.

See all 22 papers

Explore similar work

CardsList

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

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

  2. 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

    Columbia University New York, USA · Independent Researcher San Jose, USA · University of California, Los Angeles Los Angeles, USA +2

  3. DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models

    Jun 25, 2026Yuxuan Yang, Feiyang Li, Yile Wang

    College of Computer Science and Software Engineering, Shenzhen University