Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Paper • 2512.15687 • Published • 22
Yujun Zhou
yujunzhou
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
Emergent Social Intelligence Risks in Generative Multi-Agent Systems updated a model 17 days ago
yujunzhou/MATH-TTT-Qwen3-4B-Base-Semantic-ClipHigh-Ent0.003-RandomNovelty published a model 17 days ago
yujunzhou/MATH-TTT-Qwen3-4B-Base-Semantic-ClipHigh-Ent0.003-RandomNoveltyOrganizations
None yet
submitted a
paper to Daily Papers 4 months ago