1 minute read

1 minute read

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

12 minute read

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

[Agent] ToolRL: Reward is All Tool Learning Needs — tool-use RL에서 reward 설계만 바꿔도 되는가

9 minute read

[Agent] ToolRL: Reward is All Tool Learning Needs

[Agent] SynPlanResearch-R1: 랜덤 tool plan + cue로 합성한 cold-start 데이터가 RL의 탐색 천장을 올린다

9 minute read

[Agent] SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans