Daily AI Papers Briefing (2026-07-28)

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. DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
https://huggingface.co/papers/2607.20465
2. Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
https://huggingface.co/papers/2607.22529
3. Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
https://huggingface.co/papers/2607.21653
4. Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
https://huggingface.co/papers/2607.21503
5. Interactive Training 2: Auditable Control Plane for Live Model Training
https://huggingface.co/papers/2607.18314