研究人员开发了两个新框架EmoDistill和EvoEmo，通过融入情感策略来增强语言模型代理的谈判能力。EmoDistill通过选择和表达过程专注于将情感谈判技能蒸馏到代理中，在高风险领域实现更高的效用。EvoEmo利用进化强化学习优化多轮价格谈判中的动态情感表达，在成功率和效率方面优于基线策略。这两种方法都强调了情感在代理交互中的战略重要性，超越了简单的偏好对齐。 AI
影响 这些框架表明，战略性情感表达可以显著提高LLM代理在复杂谈判任务中的表现，可能带来更复杂、更有效的AI交互。
排序理由 两篇学术论文介绍了用于LLM代理的新颖框架。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.26785v1 Announce Type: cross Abstract: Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In adversarial negotiation, however, this alignment can become a vulnerability: emotional…
arXiv:2509.04310v4 Announce Type: replace Abstract: Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, exis…
Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In adversarial negotiation, however, this alignment can become a vulnerability: emotionally framed language may steer agents toward the cou…