Tianyi Xu

tianyi0216

·

https://tianyi0216.github.io/

tianyi0216

AI & ML interests

Machine Learning, Deep Learning, Computer Vision

Recent Activity

authored a paper 3 days ago

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

upvoted a paper 4 days ago

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

upvoted a paper 4 days ago

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

View all activity

Organizations

tianyi0216 's papers 3

arxiv:2610.04184

arxiv:2605.11136

arxiv:2602.05400