Search papers, labs, and topics across Lattice.
This paper introduces Conversation Uncertainty-aware Planning (CUP), a framework that integrates language models with structured planning to improve goal-oriented conversational systems. CUP uses a language model to propose actions and a planner to evaluate their long-term impact on reducing uncertainty about the user's intent. Experiments on conversational benchmarks demonstrate that CUP improves success rates and reduces the number of interaction turns compared to existing approaches by enabling more efficient information acquisition and earlier commitment.
Goal-oriented dialogue agents can achieve higher success rates with fewer turns by explicitly planning to reduce uncertainty about user intent.
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 support flexible interactions but lack long-horizon decision making, resulting in poor coordination between information acquisition and target commitment. To address this limitation, we formulate goal-oriented conversation as an uncertainty-aware sequential decision problem, where uncertainty serves as a guiding signal for multi-turn decision making. We propose a Conversation Uncertainty-aware Planning framework (CUP) that integrates language models with structured planning: a language model proposes feasible actions, and a planner evaluates their long-term impact on uncertainty reduction. Experiments on multiple conversational benchmarks show that CUP consistently improves success rates while requiring fewer interaction turns. Further analysis demonstrates that uncertainty-aware planning contributes to more efficient information acquisition and earlier confident commitment.