从视觉感知到深度共情：一种利用多模态大语言模型和多智能体协作的房屋-树-人绘画自动评估框架
From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
AI总结：
本文提出利用多模态大语言模型和多智能体协作，开发自动评估房屋-树-人绘画测试的框架，以提升投射评估的标准化和效率。
摘要：
背景：自1948年由约翰·布克引入的房屋-树-人（HTP）绘画测试，仍然是临床心理学中广泛使用的投射技术。然而，它长期以来面临异质评分标准、依赖考官主观经验以及缺乏统一量化编码系统等挑战。结果：定量实验显示，多模态大语言模型（MLLM）解释与人类专家解释之间的平均语义相似度约为0.75（标准差约为0.05）。在结构导向的专家数据集中，这一相似度上升至0.85，表明专家级的基准理解。定性分析显示，多智能体系统通过整合社会心理视角和去污名化叙述，有效纠正了视觉幻觉，并产生了具有高生态效度和内部一致性的心理报告。结论：研究结果证实了多模态大模型作为标准化投射评估工具的潜力。所提出的多智能体框架通过分工，将特征识别与心理推断解耦，并为数字心理健康服务提供了一种新的范式。关键词：房屋-树-人测试；多模态大语言模型；多智能体协作；余弦相似度；计算心理学；人工智能
英文摘要：
Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced challenges such as heterogeneous scoring standards, reliance on examiners subjective experience, and a lack of a unified quantitative coding system. Results: Quantitative experiments showed that the mean semantic similarity between Multimodal Large Language Model (MLLM) interpretations and human expert interpretations was approximately 0.75 (standard deviation about 0.05). In structurally oriented expert data sets, this similarity rose to 0.85, indicating expert-level baseline comprehension. Qualitative analyses demonstrated that the multi-agent system, by integrating social-psychological perspectives and destigmatizing narratives, effectively corrected visual hallucinations and produced psychological reports with high ecological validity and internal coherence. Conclusions: The findings confirm the potential of multimodal large models as standardized tools for projective assessment. The proposed multi-agent framework, by dividing roles, decouples feature recognition from psychological inference and offers a new paradigm for digital mental-health services. Keywords: House-Tree-Person test; multimodal large language model; multi-agent collaboration; cosine similarity; computational psychology; artificial intelligence
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。
