CLEAT: Learning Value-Guided Clarification for Interactive Agents
arXiv:2610.12655v1 Announce Type: new Abstract: LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. We study this...
Read more: https://arxiv.org/abs/2610.12655
Scan with your phone
Scan with your phone