HF Daily Papers · 2026-10-17

HF Daily Papers 精选（15 篇，按社区票数排序）

  • [451▲] Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation — https://arxiv.org/abs/2610.21601
  • [277▲] OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use — https://arxiv.org/abs/2610.22200
  • [230▲] FDE-Gym: The Last Mile of AI Delivery — https://arxiv.org/abs/2610.22350
  • [198▲] RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment — https://arxiv.org/abs/2610.17665
  • [189▲] Self-Evolving Agent Harness — https://arxiv.org/abs/2610.18813
  • [142▲] MJev-Spatial: System One Spatial Intelligence via Native Attention Matching — https://arxiv.org/abs/2610.22276
  • [94▲] MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments — https://arxiv.org/abs/2610.20939
  • [53▲] VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models — https://arxiv.org/abs/2610.21306
  • [48▲] Mosaic: Multi-Session Agentic Reinforcement Learning — https://arxiv.org/abs/2610.22174
  • [33▲] Can World and Action Modeling Benefit Each Other under Unified Causal Training? — https://arxiv.org/abs/2610.21095
  • [29▲] WorldCast: Exploring Intelligent Visual Generation in World State Prediction — https://arxiv.org/abs/2610.20731
  • [27▲] OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling — https://arxiv.org/abs/2610.22355
  • [25▲] Data World: Scaling Data Environments from Scratch — https://arxiv.org/abs/2610.21656
  • [24▲] MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering — https://arxiv.org/abs/2610.22344
  • [20▲] Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL — https://arxiv.org/abs/2610.21439