arxiv:2510.03222
Guanhua Huang
Carlanlarkk
AI & ML interests
None yet
Recent Activity
authored
a paper
17 days ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
17 days ago
Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and
Planning
Organizations
None yet
models
0
None public yet
datasets
0
None public yet