arxiv:2610.27528
sgq
gqbond
·
AI & ML interests
reinforcement learning, LLM as a judge
Recent Activity
new activity 7 days ago
gqbond/DeCert-Llama-3.1-8B:Add library name, link to paper and code upvoted a paper 8 days ago
SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training upvoted a paper 10 days ago
Trust Region Policy DistillationOrganizations
None yet