arc-agi-2

Tag

Cards List
#arc-agi-2

Meta^n: Recursive Self-Improvement through Emergent Depth

Hugging Face Daily Papers · 2026-08-25 Cached

This paper introduces Meta^n, a method for recursive self-improvement in LLM agents by applying a fixed meta-operation to expand reasoning depth, outperforming prior approaches on benchmarks like ARC-AGI-2.

0 favorites 0 likes
#arc-agi-2

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

arXiv cs.AI · 2026-07-13 Cached

ARCANA is a reflective multi-agent framework that decomposes ARC-AGI-2 abstract reasoning tasks into iterative perception, hypothesis generation, symbolic execution, and reflective refinement, improving reasoning efficiency under strict constraints.

0 favorites 0 likes
← Back to home

Submit Feedback