Daily AI Papers Briefing (2026-08-10)

ずんだもんのHugging Faceニュース · Aug 9, 2026 · 3m

【本日の論文】

1. AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

https://huggingface.co/papers/2608.05987

2. OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

https://huggingface.co/papers/2607.28609

3. Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval

https://huggingface.co/papers/2608.01481

4. WorldClaw: Agentic 3D Open-World Generation at Scale

https://huggingface.co/papers/2608.05248

5. GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?…