Daily AI Papers Briefing (2026-10-12)

ずんだもんのHugging Faceニュース · Oct 12, 2026 · 3m

【本日の論文】

1. AgentGarten: Code Worlds for Evolving Agents

https://huggingface.co/papers/2610.12374

2. Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?

https://huggingface.co/papers/2610.08215

3. TokenRouter: Efficient Serving System for Token-Level LLM Routing

https://huggingface.co/papers/2610.12242

4. From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

https://huggingface.co/papers/2610.06100

5. MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

https://huggingface.co/papers/2610.11959