Daily AI Papers Briefing (2026-09-11)

ずんだもんのHugging Faceニュース · Sep 10, 2026 · 3m

【本日の論文】

1. Show-Harness: Just a VLM Agent Can Play Robots

https://huggingface.co/papers/2609.10522

2. AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

https://huggingface.co/papers/2609.08572

3. Programmable World Model

https://huggingface.co/papers/2609.10540

4. WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

https://huggingface.co/papers/2609.05405

5. SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

https://huggingface.co/papers/2609.08149