LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents 事件

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents arXiv:2606.06087v1 Announce Type: new Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext. We present LatentSkill, a framework that converts textual skills into plug-and-play LoRA adapters through a pretrained hypernetwork. LatentSkill store