Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Paper
•
2512.15687
•
Published
•
17
Sidi Lu
desire2020
AI & ML interests
NLG
Recent Activity
authored
a paper
8 days ago
Controllable Text Generation with Neurally-Decomposed Oracle
authored
a paper
8 days ago
Long Text Generation via Adversarial Training with Leaked Information
authored
a paper
8 days ago
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Organizations
None yet
upvoted
a
paper
8 days ago