SAGE：利用未来感知的状态-动作增强来引导对话生成
SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation
AI总结：
提出SAGE方法，通过状态-动作链引入潜变量控制对话长程行为，并结合自我改进流程优化对话轨迹，提升了情感智能指标且保持LLM基准能力。
摘要：
大型语言模型的最新进展在面向任务的应用中展示了令人印象深刻的能力，但构建能够进行自然、策略性对话的情感智能聊天机器人仍然是一个挑战。我们提出了一种名为 SAGE 的新方法，该方法使用潜变量来控制对话生成中的长程行为。我们方法的核心是状态-动作链（SAC），它通过引入封装对话轮次之间情感状态和对话策略的潜变量，来增强标准的语言模型微调。在推理期间，这些变量在每个响应之前生成，从而实现对对话进展的粗粒度控制，同时保持自然的交互模式。我们还引入了一个自我改进流程，利用对话树搜索、基于 LLM 的奖励建模和有针对性的微调来优化对话轨迹。我们的实验结果表明，使用该方法训练的模型在情感智能指标上表现出改进的性能，同时在 LLM 基准测试上保持强大的能力。我们潜变量的离散特性促进了基于搜索的策略，并为未来将强化学习应用于对话系统奠定了基础，在对话系统中学习可以在状态层面而不是 token 层面进行。
英文摘要：
Recent advances in large language models have demonstrated impressive capabilities in task-oriented applications, yet building emotionally intelligent chatbots that can engage in natural, strategic conversations remains a challenge. We present a novel approach called SAGE that uses latent variables to control long-horizon behavior in dialogue generation. At the core of our method is the State-Action Chain (SAC), which augments standard language model fine-tuning by introducing latent variables that encapsulate emotional states and conversational strategies between dialogue turns. During inference, these variables are generated before each response, enabling coarse-grained control over dialogue progression while maintaining natural interaction patterns. We also introduce a self-improvement pipeline that leverages dialogue tree search, LLM-based reward modeling, and targeted fine-tuning to optimize conversational trajectories. Our experimental results show that models trained with this approach demonstrate improved performance in emotional intelligence metrics while maintaining strong capabilities on LLM benchmarks. The discrete nature of our latent variables facilitates search-based strategies and provides a foundation for future applications of reinforcement learning to dialogue systems, where learning can occur at the state level rather than the token level. https://github.com/apple/ml-sage-dialog-gen
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。
