Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
作者: Bohan Lin, Hejia Geng, Xinyi Xie, Heng Zhou, Qinghua Xing, Bo Liu, Chen Zhang, Yudong Zhang
分类: cs.AI
发布日期: 2026-08-10
🔗 代码/项目: GITHUB
💡 一句话要点
提出Emotion2Skill框架以解决LLM代理技能选择问题
🎯 匹配领域: 支柱七:动作重定向 (Motion Retargeting) 支柱八:物理动画 (Physics-based Animation)
关键词: 情感信号 技能选择 决策系统 大语言模型 智能代理 情感轨迹 SOP重写
📋 核心要点
- 现有技能基础的LLM代理在选择技能时仅依赖文本信号,未能利用模型内部的情感状态,导致决策效率低下。
- Emotion2Skill框架通过提取LLM内部的情感向量,将其融入技能选择和演化过程,提升决策的准确性和适应性。
- 在WebShop和ALFWorld的实验中,Emotion2Skill显著提高了成功率,分别提升26.9%和25.5%,超越所有基线方法。
📝 摘要(中文)
在技能基础的LLM代理中,现有方法仅依赖文本信号进行技能选择,忽视了模型内部的情感信号。本文提出Emotion2Skill框架,提取LLM内部情感向量,应用于技能选择和演化。通过分析情感轨迹,识别内部状态的突变,指导技能调用的优化。实验结果表明,Emotion2Skill在WebShop和ALFWorld上显著提升了成功率,展示了情感表示在决策中的有效性。
🔬 方法详解
问题定义:现有的技能选择方法主要依赖文本描述和经验规则,忽视了模型内部的情感信号,导致决策过程缺乏有效性和灵活性。
核心思路:本文提出Emotion2Skill框架,通过提取LLM内部的27维情感状态,将其作为决策信号融入技能选择和演化过程,以提高代理的适应性和决策质量。
技术框架:Emotion2Skill的整体架构包括情感状态的提取模块、技能选择模块和技能演化模块。在每个决策步骤中,从残差流中提取情感向量,并将其映射到路由提示中。
关键创新:最重要的创新在于将LLM内部的情感表示用于代理级决策,而不仅仅是用于后期分析或输出引导。这一方法使得情感信号成为有效的决策依据。
关键设计:在模型设计中,情感状态的提取采用了27维向量,结合了信心门控机制,以确保情感信息的有效注入。此外,情感轨迹分析用于识别技能调用中的问题,指导针对性的SOP重写。
🖼️ 关键图片
📊 实验亮点
在WebShop和ALFWorld的实验中,Emotion2Skill框架显著提高了成功率,分别提升了26.9%和25.5%。该方法在所有基线测试中表现优异,展示了情感信号在技能选择中的重要性和有效性。
🎯 应用场景
Emotion2Skill框架具有广泛的应用潜力,特别是在需要复杂决策的智能代理系统中,如机器人、虚拟助手和游戏AI等。通过有效利用内部情感信号,该框架能够提升代理的决策能力和适应性,未来可能在多种领域产生深远影响。
📄 摘要(原文)
Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved. Recent interpretability work has shown that LLMs maintain linear emotion representations that causally influence behavior; however, these representations have been exploited only for post-hoc analysis or direct output steering, and have not been used to inform agent-level decision-making. We propose Emotion2Skill, a framework that extracts LLM-internal emotion vectors and incorporates them into both skill selection and skill evolution. At each decision step, a 27-dimensional emotion state is extracted from the residual stream and mapped to a confidence-gated summary injected into the routing prompt. Beyond online selection, emotion trajectories are analyzed for abrupt internal-state shifts to pinpoint problematic skill invocations, guiding targeted SOP rewriting that replaces the coarse binary outcome signal of prior methods. On WebShop and ALFWorld, Emotion2Skill with Qwen3-8B improves over the Zero-Shot baseline by +26.9% success rate and +25.5% average success respectively, outperforming all baselines on both benchmarks with consistent gains on Qwen3-14B. Co-activation analysis further reveals semantically coherent emotion--skill pairings, confirming that the routing improvements reflect meaningful internal-state signals rather than opaque statistical correlations. These results establish LLM-internal emotion representations as an effective decision-level signal for orchestrating agent skill systems, extending their utility beyond interpretability and output steering. The code is available at https://github.com/BoHan-LIN04/Emotion2Skill.