TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
Paper
•
2601.18292
•
Published
•
9
cheng
zheng123
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 6 hours ago
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
upvoted
a
paper
about 6 hours ago
FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning
Organizations
None yet
upvoted
2
papers
about 6 hours ago