Xinyan Guan

xinyan233333

·

gxy-gxy

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

upvoted a paper 3 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

authored a paper 6 days ago

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

View all activity

Organizations

None yet

Papers 4

arxiv:2607.29211

arxiv:2502.01142

arxiv:2501.03936

arxiv:2411.11504

models 5

xinyan233333/CaRL-14B

15B • Updated Apr 15 • 10

xinyan233333/CaRL-8B

8B • Updated Apr 15 • 12

xinyan233333/DeepRAG-8b

8B • Updated Feb 17 • 7

xinyan233333/DeepRAG-7b

8B • Updated Feb 17 • 10 • 2

xinyan233333/test

33B • Updated Sep 24, 2025 • 4

datasets 0

None public yet