MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
MMSearch-OPD hardens multimodal questions and jointly trains long-horizon search agents with RL and distillation.
1 stories, newest first · one card per story
MMSearch-OPD hardens multimodal questions and jointly trains long-horizon search agents with RL and distillation.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views