用大模型生成候选动作，智能选择最优对话策略。
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
- 用冻结大模型生成高质量对话动作候选，缩小决策空间。
- 三轮内完成对话，成功率超94%，部分场景超97%。
- 结合用户情绪动态调整策略，适合需要共情的交互场景。
大型语言模型（LLM）代理在反应式对话中表现优异，但在主动、目标驱动的交互中因短视解码和高昂规划成本而受限。我们提出DialogXpert，利用冻结的LLM每轮生成少量高质量候选动作，并通过基于时序差分学习训练的紧凑Q网络，在固定BERT嵌入空间中选择最优动作。该系统实时追踪用户情绪，使每个决策既推动任务进展，又建立真实共情连接。在谈判、情感支持和辅导等基准测试中，DialogXpert可在三轮内达成目标，成功率超过94%；使用更大规模的LLM先验时，成功率突破97%，显著提升谈判效果。该框架实现了可扩展的实时、战略性和情绪智能对话规划。代码见 https://github.com/declare-lab/dialogxpert/
原文摘要 · Abstract (English)
Large-language-model (LLM) agents excel at reactive dialogue but struggle with proactive, goal-driven interactions due to myopic decoding and costly planning. We introduce DialogXpert, which leverages a frozen LLM to propose a small, high-quality set of candidate actions per turn and employs a compact Q-network over fixed BERT embeddings trained via temporal-difference learning to select optimal moves within this reduced space. By tracking the user's emotions, DialogXpert tailors each decision to advance the task while nurturing a genuine, empathetic connection. Across negotiation, emotional support, and tutoring benchmarks, DialogXpert drives conversations to under $3$ turns with success rates exceeding 94\% and, with a larger LLM prior, pushes success above 97\% while markedly improving negotiation outcomes. This framework delivers real-time, strategic, and emotionally intelligent dialogue planning at scale. Code available at https://github.com/declare-lab/dialogxpert/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。