TEA-Bench: 一种工具增强情感支持对话代理的系统性基准测试
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
AI总结：
本文提出TEA-Bench，首个评估工具增强情感支持对话代理的交互式基准，通过真实情感场景和工具环境评估情感支持质量和事实性。实验表明工具增强提升情感支持质量并减少幻觉，但效果依赖模型能力。
摘要：
情感支持对话需要不仅有情感表达，还需要有事实性工具支持以提供可信指导。然而，现有ESC系统和基准大多集中在纯文本环境中的情感支持，忽视了外部工具如何在多轮情感支持中提供事实基础并减少幻觉。我们引入TEA-Bench，首个评估工具增强情感支持对话代理的交互式基准，包含真实情感场景、MCP式工具环境和过程级指标，共同评估情感支持的质量和事实性。实验表明，工具增强通常提升情感支持质量并减少幻觉，但收益强烈依赖模型能力：更强模型更有效地使用工具，而较弱模型收益有限。我们进一步发布TEA-Dialog数据集，发现监督微调在分布内支持表现良好但泛化差。我们的结果强调了工具使用在构建可靠情感支持代理中的重要性。代码和数据可在https://github.com/XingYuSSS/TEA-Bench找到。
英文摘要：
Emotional Support Conversation requires not only affective expression but also grounded instrumental support to provide trustworthy guidance. However, existing ESC systems and benchmarks largely focus on affective support in text-only settings, overlooking how external tools can enable factual grounding and reduce hallucination in multi-turn emotional support. We introduce TEA-Bench, the first interactive benchmark for evaluating tool-augmented agents in ESC, featuring realistic emotional scenarios, an MCP-style tool environment, and process-level metrics that jointly assess the quality and factual grounding of emotional support. Experiments on nine LLMs show that tool augmentation generally improves emotional support quality and reduces hallucination, but the gains are strongly capacity-dependent: stronger models use tools more selectively and effectively, while weaker models benefit only marginally. We further release TEA-Dialog, a dataset of tool-enhanced ESC dialogues, and find that supervised fine-tuning improves in-distribution support but generalizes poorly. Our results underscore the importance of tool use in building reliable emotional support agents. Our code and data can be found in https://github.com/XingYuSSS/TEA-Bench.
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。
