MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
Paper • 2605.01347 • Published • 1
Avicii Tom
jianzewang
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate upvoted a paper 12 days ago
TTPO: Test-Time Policy OptimizationOrganizations
None yet