AI & ML
Meta$^n$: Recursive Self-Improvement through Emergent Depth
arXiv eess.SY0 views
arXiv:2608.24735v2 Announce Type: replace-cross Abstract: 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, $\Omega$, 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 a library of callable helpers. Because $\Omega$ never changes, it cannot destabilize the system, and because its input strictly grows, each layer reasons from a higher vantage than the last. Depth is set by convergence rather than fixed in advance, and an evolutionary archive searches over layer chains. Across two backbones, Meta$^n$ outperforms prior self-improving agents on all eight benchmark families. The sharpest case is ARC-AGI-2, built to resist skill memorization, where it alone scores above zero. Ablations indicate that most of the gain from recursion comes from the conditioning each layer passes to the next, and distinct layer roles emerge with depth although no prompt prescribes them. Code available at https://github.com/minnesotanlp/meta-n
Source:https://arxiv.org/abs/2608.24735PreviousA Differentiable Composite Approximation Framework for Autonomous Underwater Vehicle Maneuvering Modeling from Sea-Trial DataNextSPROUT: The Open-Source Soft Growing Robot for Search and Rescue
Related posts
Thống kê hiệu suất Al Ahli vs Al Nassr: Phép thử cực đại cho hàng công chủ nhà
0dev.to Data
Phân tích số liệu vòng 10 Bundesliga: Thách thức chiến thuật của FC Koln trước Bayern Munich
0dev.to Data
Dấu ấn chiến thuật của Hansi Flick: Biến số Frenkie de Jong giúp Barcelona ngược dòng trước Atletico Madrid
0dev.to Data
PMO Support Services in the UAE: What Effective Program Governance Actually Requires
0dev.to News
The draft is not the send
0dev.to Discuss

My First GitHub Issue & My First Forem (DEV.to) Issue 🚀
0dev.to Discuss