ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
Abstract
We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations, and a reflective agent synthesizes failure driven feedback for the next turn. These agents communicate through a shared differentiable blackboard and are scheduled by a learned meta controller. The design combines structured program search with adaptive multi turn correction, improving reasoning efficiency and solution quality on challenging abstract transformation tasks.
Cite
@article{arxiv.2607.09059,
title = {ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning},
author = {Kunbo Zhang and Lei Fu and Zeyu Wang and Zijing Liu and Kejian Tong},
journal= {arXiv preprint arXiv:2607.09059},
year = {2026}
}