{"ID":6497850,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09059","arxiv_id":"2607.09059","title":"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.","short_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 grap...","url_abs":"https://arxiv.org/abs/2607.09059","url_pdf":"https://arxiv.org/pdf/2607.09059v1","authors":"[\"Kunbo Zhang\",\"Lei Fu\",\"Zeyu Wang\",\"Zijing Liu\",\"Kejian Tong\"]","published":"2026-07-10T03:03:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}