Cite
Notes
Only stored in your browser.
Attribution
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
arXiv 2026
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning
arXiv 2025
Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness
arXiv 2023
from 3 papers
Ying Wen
Ziyu Wan
Chaochao Lu
Chenjia Bai
Han Qi
Hanjing Wang
HaoYuan Chen
Jun Wang
Linyi Yang
Mark Schmidt