Meta^n: Recursive Self-Improvement Hits 0.331 on ARC-AGI-2
burny_tech · x · 2026-08-31
The paper proposes Meta^n, a recursive self-improvement architecture where a fixed meta-operation applies to its own products. Deeper layers inspect both failures and the code causing them to refine strategies. It scores 0.331 on ARC-AGI-2, significantly outperforming Gödel Agent and OpenEvolve.
Related event: Meta^n Architecture Enables Recursive Self-Improvement in AI Agents(3 posts)→
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Dev workflow: Astra for tedious tasks, Claude for ideas not implementation — menhguin · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16