Xuyan Ye

LulaCola

·

https://xuyan923r.github.io/

Xuyan923r

AI & ML interests

LLM Reasoning, Self-Evolving Agent

Recent Activity

upvoted a paper about 2 hours ago

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

authored a paper 2 months ago

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

upvoted a paper 2 months ago

The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

View all activity

Organizations

Papers 3

arxiv:2605.11182

arxiv:2603.14465

arxiv:2601.13761

models 2

LulaCola/DARC_Solver_Qwen3-8B

8B • Updated Mar 8 • 10

LulaCola/DARC_Questioner_Qwen3-8B

8B • Updated Mar 8 • 5

datasets 3

LulaCola/AgentProcessBench

Viewer • Updated Mar 18 • 1k • 266 • 16

LulaCola/DARC_Corpus

Viewer • Updated Mar 8 • 60k • 17

LulaCola/DARC_Solver_Train

Viewer • Updated Mar 8 • 53.2k • 21