DialogXpert：通过基于在线价值强化学习与LLM先验驱动智能且情感感知的对话
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
AI总结：
DialogXpert利用冻结LLM生成候选动作，结合紧凑Q网络进行在线价值强化学习，实现情感感知的主动对话，在多个基准中成功率超94%，并显著提升谈判效果。
摘要：
大型语言模型（LLM）智能体擅长反应式对话，但由于短视解码和昂贵的规划，在主动的、目标驱动的交互中表现不佳。我们引入了DialogXpert，它利用冻结的LLM在每轮提出一小部分高质量的候选动作，并采用一个在固定BERT嵌入上的紧凑Q网络，通过时序差分学习训练，在此缩减空间内选择最优动作。通过跟踪用户的情绪，DialogXpert调整每个决策以推进任务，同时培养真诚、共情的联系。在谈判、情感支持和辅导基准测试中，DialogXpert将对话控制在3轮以内，成功率超过94%，并且借助更大的LLM先验，成功率提升至97%以上，同时显著改善谈判结果。该框架实现了大规模实时、战略性和情感智能的对话规划。代码可在https://github.com/declare-lab/dialogxpert/获取。
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
