KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
Paper • 2604.12627 • Published • 80
TIANYI
BIMU233
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance authored a paper about 8 hours ago
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks upvoted a paper about 9 hours ago
From Word to World: Can Large Language Models be Implicit Text-based World Models?Organizations
None yet