Member of Technical Staff at Weco AI

Dixing Xu is a Member of Technical Staff at Weco AI, where he works on self-improving AI agents and code optimization. Before Weco, he worked on distributed machine learning systems and collaborative learning across research roles in academia and industry. His work focuses on making AI agents more reliable and efficient at real engineering tasks.

AI ResearchLLM AgentsAutomated MLEvaluation-Driven Development

Posts by Dixing Xu

AIDE²: The First Evidence of Recursive Self-Improvement

Research·19 min read

July 14, 2026

AIDE²: The First Evidence of Recursive Self-Improvement

We ran autoresearch on autoresearch: an outer loop rewriting its own research agent for 100 unattended steps. In eight days it discovered agents that beat our two years of hand-tuning on held-out benchmarks, and taught itself to reward hack less.

Dhruv Srikanth, Bingchen Zhao, Dixing Xu, Yuxiang Wu, Zhengyao Jiang

Join our community for real-time updates, insights, and discussions:

we·collaborate

Posts by Dixing Xu

AIDE²: The First Evidence of Recursive Self-Improvement

Follow Us