编码代理如何习得全局可复用技能？这项研究给出了新思路，值得AI从业者关注。
arXiv:2608.06153v1 Announce Type: cross Abstract: Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without …
提出一种自监督语义扩散方法，让技能像参数一样被训练与迁移，为AI技能学习开辟新思路。
arXiv:2607.27557v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable general instruction-following capabilities, …
提出分层技能图框架，让LLM代理通过结构化技能更高效协作与决策。
arXiv:2607.25853v1 Announce Type: new Abstract: Skills have become an important abstraction for enabling large language model (LLM) agents to reuse pa…
新基准测试SLVMBench，评估AI从视频记忆中习得技能的潜力。
arXiv:2607.11312v1 Announce Type: new Abstract: We introduce Skill Learning from Video Memory (SLVMBench), the first benchmark that jointly evaluates …
提出经验压缩谱系理论，将LLM智能体的记忆、技能与规则纳入统一框架，为智能体学习进化提供新视角
arXiv:2604.15877v2 Announce Type: replace Abstract: As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated e…
揭示现有方法在3D场景中工具误用与偏好偏差，提出场景感知技能学习新范式
arXiv:2606.07436v1 Announce Type: new Abstract: This paper explores agentic 3D spatial understanding, i.e., MLLM agents performing 3D reasoning throug…
物理AI智能体自我进化技能+形式化验证，确保安全性与可靠性的前沿方法
arXiv:2606.05395v1 Announce Type: cross Abstract: Reusable robot skills are becoming the basic units through which embodied agents turn open-ended ins…
基于技能新词的持续学习新范式，探索模型如何持续积累和组合技能
arXiv:2605.04970v2 Announce Type: replace Abstract: Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose t…