热点
"RLVMR" 相关文章
教会7B模型“自我思考”！腾讯RLVMR刷新智能体认知，长程任务表现直追GPT-4o
PaperWeekly 2025-08-18T16:03:14.000000Z
RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
cs.AI updates on arXiv.org 2025-07-31T04:48:18.000000Z