ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
Learn how ARCANA, a multi-agent framework, synthesizes programs for ARC-AGI-2 reasoning tasks under strict constraints, and apply its principles to your own program synthesis projects
- Decompose complex tasks into iterative perception, hypothesis generation, symbolic execution, and reflective refinement using ARCANA's framework
- Implement a perceptual grounding agent to build object-centric scene graphs from raw data
- Design a latent program policy to propose diverse DSL programs for task solving
- Verify candidate programs using a symbolic executor on demonstrations
- Apply reflective refinement to improve program synthesis results
Researchers and developers working on artificial general intelligence (AGI) and program synthesis can benefit from ARCANA's reflective multi-agent approach to solve complex reasoning tasks
💡 ARCANA's reflective multi-agent approach can effectively solve complex reasoning tasks under strict constraints by decomposing tasks into iterative perception, hypothesis generation, symbolic execution, and reflective refinement
🤖 Introducing ARCANA: a collaborative multi-agent framework for program synthesis in ARC-AGI-2 reasoning tasks 🚀
Key Takeaways
Learn how ARCANA, a multi-agent framework, synthesizes programs for ARC-AGI-2 reasoning tasks under strict constraints, and apply its principles to your own program synthesis projects
Full Article
Abstract:
arXiv:2607.09059v1 Announce Type: new 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,
DeepCamp AI