1 minute read

1 minute read

[VLM] VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents — reasoning을 world model 구조로 강제하면 3B가 GPT-5를 넘는다

8 minute read

[VLM] VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

[Agent] BAGEN: Are LLM Agents Budget-Aware? — agent는 자기가 얼마나 쓸지 모른다

10 minute read

[Agent] BAGEN: Are LLM Agents Budget-Aware?

[Agent] RAGEN-2: Reasoning Collapse in Agentic RL — entropy가 멀쩡해도 reasoning은 무너진다

12 minute read

[Agent] RAGEN-2: Reasoning Collapse in Agentic RL