ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning

2026-07-10 · Kunbo Zhang, Lei Fu, Zeyu Wang, Zijing Liu, Kejian Tong arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.09059

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis

Improving Multi-modal Large Language Model through Boosting Vision Capabilities

2024-10-17 · Yanpeng Sun, Huaxin Zhang, Qiang Chen, Xinyu Zhang 외

We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multi…

Decoder Language Modeling Language Modelling Large Language Model+1

The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge

2025-12-22 · Angjelin Hila arxiv

We examine epistemological threats posed by human and LLM interaction. We develop collective epistemology as a theory of epistemic warrant distributed across human collectives, using bounded rationality and dual process …

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

2025-09-24 · Yandan Yang, Baoxiong Jia, Shujie Zhang, Siyuan Huang arxiv

Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While rec…

Indoor Scene Synthesis Scene Generation

LTLf Synthesis on First-Order Agent Programs in Nondeterministic Environments

2024-10-01 · Till Hofmann, Jens Claßen

We investigate the synthesis of policies for high-level agent programs expressed in Golog, a language based on situation calculus that incorporates nondeterministic programming constructs. Unlike traditional approaches f…

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

2026-02-03 · Zhengbo Jiao, Shaobo Wang, Zifan Zhang, Wei Wang 외 arxiv

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme sc…

Synthetic Data Generation Image Generation