Daily AI Papers Briefing (2026-08-31)

Podliアプリで聴く 🎧

お気に入りの番組をフォローして、オフラインでも車内でもCarPlayやAndroid Autoで再生。いつでも続きから聴けます。無料でお試しできます。

【本日の論文】
1. Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
https://huggingface.co/papers/2608.25518
2. PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
https://huggingface.co/papers/2608.27345
3. UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
https://huggingface.co/papers/2608.27456
4. TTPO: Test-Time Policy Optimization
https://huggingface.co/papers/2608.27448
5. Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
https://huggingface.co/papers/2608.26872