Hugging FaceHugging Face 일일 논문
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence.
#강화학습
5건 · 최신순
Hugging FaceHugging Face 일일 논문
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can yield highly similar trajectories, reducing within-group reward variation and weakening…
Hugging FaceHugging Face 일일 논문
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the…
Hugging FaceHugging Face 일일 논문
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on student-generated trajectories.
Hugging FaceHugging Face 일일 논문
Mosaic: Multi-Session Agentic Reinforcement Learning
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context.