Meta$^n$: Recursive Self-Improvement through Emergent Depth
Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those that edit themselves must leave part of their own editing machinery untouched to stay stable, capping the meta-depth they realize at roughly two. We present Meta$^n$, which keeps the meta-operation fixed and recurses on its input instead. That operation, $Ω$, is applied repeatedly to its own products, reading the traces of the solver stack below together with the code that produced them, then writing the next layer as a strategic pre-process and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 59%AI’s recursive self-improvement might not come so quickly after all →
- PossiblePossibly related (embedding) · 52%AI’s recursive self-improvement might not come so quickly after all - MIT Technology Review →
- FuzzyOverlapping authors or contributors · 62%browser-use/browser-use →
“Shared author/contributor keys: lee”
- LinkedLinked via arxiv author · 85%Zae Myung Kim →
“Meta$^n$: Recursive Self-Improvement through Emergent Depth”
- LinkedLinked via arxiv author · 85%Young-Jun Lee →
“Meta$^n$: Recursive Self-Improvement through Emergent Depth”
- LinkedLinked via arxiv author · 85%Seungyeon Jwa →
“Meta$^n$: Recursive Self-Improvement through Emergent Depth”
- LinkedLinked via arxiv author · 85%Dongyeop Kang →
“Meta$^n$: Recursive Self-Improvement through Emergent Depth”
- PossiblePossibly related (embedding) · 54%Recursive Self-Improvement in LLMs - Blockchain Council →