3 papers
cs.LG2026
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Yi Duan, Ying Liu, Zirui Tang +30
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 improveme…
cs.CL2026
Are We Ready For An Agent-Native Memory System?
Wei Zhou, Xuanhe Zhou, Shaokun Han +5
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information stora…
cs.DB2026
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
Wei Zhou, Jun Zhou, Haoyu Wang +16
Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them, which is essential for a wide range of data-centric app…