paper-with-me

홈 › Papers

From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design

2026-06-08 · Dun Li, Jiatao Li, Hongzhi Li arxiv

Recursive self-design refers to AI-assisted modification of the mechanisms by which an AI system is built, evaluated, and improved. This paper treats MetaAI not as a mature paradigm, but as a working term for a human-seeded, AI-expanded development pattern in which the design space itself becomes a target of modification. We propose an operational evidence framework with four criteria: inspectable target system, meta-level modifier, feedback-directed selection, and recursive continuation. We then map public systems, including Darwin Goedel Machine (DGM), STOP, Goedel Agent, and ShinkaEvolve, against these criteria. DGM provides the most direct currently reported evidence: its published results show improvement from 20% to 50% on SWE-bench Verified and from 14.2% to 30.7% on full Polyglot after 80 iterations, with ablations suggesting that both open-ended exploration and self-improvement contribute. Finally, we provide MetaAI-Mini, a reproducible HumanEval-based protocol and codebase. Because no completed model run is included in this build, MetaAI-Mini is reported as a protocol rather than as an experimental result.

📄 PDF Abstract BibTeX arXiv:2606.09663

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

2026-09-10 · Yi Duan, Ying Liu, Zirui Tang, Haodong Chen 외 arxiv

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Ind…

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

2026-07-30 · Junlin Yang, Che Jiang, Yu Fu, Tianwei Luo 외 arxiv

Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introd…

Nidus: Externalized Reasoning for AI-Assisted Engineering

2026-04-06 · Danil Gorinevski arxiv

We present Nidus, a governance runtime that mechanizes the V-model for AI-assisted software delivery. In the self-hosting deployment, three LLM families (Claude, Gemini, Codex) delivered a 100,000-line system under proof…

MetaAID: A Flexible Framework for Developing Metaverse Applications via AI Technology and Human Editing

2022-04-04 · Hongyin Zhu

Achieving the expansion of domestic demand and the economic internal circulation requires balanced and coordinated support from multiple industries (domains) such as consumption, education, entertainment, engineering inf…

AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

2026-01-08 · Di Zhang arxiv

Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate sc…