Back to Home
arXiv AI··Papers & Tech

CLEAT: Learning Value-Guided Clarification for Interactive Agents

中文摘要

CLEAT通过价值引导的学习机制,使AI智能体能通过提问澄清用户意图,从而在面对模糊任务时做出更精准、更符合预期的决策。

English Summary

CLEAT enables AI agents to perform value-guided clarification, allowing them to ask strategic questions to resolve user ambiguity and improve task alignment and decision-making accuracy.

Original Excerpt

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 problem as interactive intent alignment through clarification. Yet clarification is useful only when the agent can turn the answer into better decisions. As training changes how the agent handles incomplete information and uses additional answers, the same clarification can become more or less useful. We introduce CLEAT (CLarification through valuE-guided Agent co-Training), a framework that co-trains a clarification-value controller and the task policy from shared interaction outcomes. We formulate residual query value to measure the task utility gained by asking rather than proceeding under the current policy, and estimate it through paired rollouts from the same interaction history. These paired returns train the controller to predict clarification value and the task policy to select useful questions and act on the answers. The controller guides subsequent rollout collection, while outcomes from the updated agent provide new value labels that allow c…