Cite
Notes
Only stored in your browser.
Attribution
Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models
arXiv 2025
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
from 2 papers
Bo Zhou
Dmitrii Khizbullin
Guanhua Huang
Jürgen Schmidhuber
Kejiao Li
Mingchen Zhuge
Mingze Wang
Qi Yi
Siheng Li
Tingqiang Xu