ARC Prize 2026 ARC-AGI-2: Qwen3.8-Flash-Next agent on 4 L4 GPUs

Thu, 05 Nov 2026 01:12:00 +0900

This is the writeup of our solution to the Kaggle competition ARC Prize 2026 ARC-AGI-2.

Code and the competition notebook: itsuitsuki/arc-prize-2026-arc-agi-2 on GitHub
This writeup as a PDF: writeup.pdf
The Kaggle notebook: nisshokuitsuki/arc-prize-2026-solution
The engine with our changes: itsuitsuki/merlin-engine, branch arc-v2.5.2

Acknowledgements

We thank the ARC Prize Foundation and Kaggle for hosting ARC Prize 2026.

We also thank the authors of the public work we build on:

Adarsh’s notebook arc-qwen-3-8-27b-agent: the objects() and diff() helpers, and a submission tool, which the model can call to record the answer of a program that reproduces the training pairs.
Russell Kirk’s notebook arcagi2-qwen38-freeform-direct and Tufa Labs’ Duck harness: a harness that leaves the choice between reasoning directly and running Python to the model.
NVIDIA’s Nemotron-SFT-ARC-AGI-v1 dataset: the name and call format of our Python tool (we have not trained on the dataset).
The ARC Prize Foundation’s arc-agi-benchmarking: the wording of our task prompt and the parsing of grids from the model’s answer.

The model stack is the work of the Qwen team (Qwen3.8-Flash-Next), Intel (W4A16 AutoRound), RadixArk and albucino (the FP8 n-gram table and the INT4 MTP drafter), AxonZeta (AZ-Focus) and dfranzen (the Kaggle copies). We serve it with halt95’s Merlin engine, a fork of vLLM.

LLM Inference on itu

ARC Prize 2026 ARC-AGI-2: Qwen3.8-Flash-Next agent on 4 L4 GPUs

Acknowledgements