引用本概念的论文(5)
- LatentSkill:面向 LLM 智能体、从上下文文本技能到权重内潜在技能 LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents arXiv 2606.06087
- 参数化技能 Parametric Skills arXiv 2606.30015
- MADA-RL：面向紧凑模型参数高效推理的多智能体辩论感知强化学习 MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models arXiv 2607.18006
- RL后训练算力应投向何处:模型规模、搜索、学习与反馈 Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback arXiv 2607.13389
- 过度思考：放大推理权重以提取已习得的秘密 Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets arXiv 2607.08173