Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents

arXiv:2402.09205v1 Announce Type: new
Abstract: Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents struggle with seeking clarification and grasping precise user intentions. To bridge this gap, we introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. Next, we propose the incorporation of model experts as the upstream in agent designs …

abstract adept agents arxiv cs.ai cs.cl cs.hc current found language language model strategies struggle tasks type understanding