Tag
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.
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.