Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation

ArXi:2604.03924v1 Announce Type: cross Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and target commitment over multiple turns. Existing approaches address this challenge from different perspectives: structured methods enable multi-step planning but rely on predefined schemas, while LLM-based approaches flexible interactions but lack long-horizon decision making, resulting in poor coordination between information acquisition and target commitment.