一种主动式多智能体对话框架用于评估自闭症中的社交语言障碍特征
A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism
AI总结：
提出TPA（思考、计划、询问）主动式多智能体对话框架，通过临床策略驱动的提问选择，在ADOS-2评估中实现82.1%的社交语言障碍特征覆盖率，比临床医生自动回放高16.6%。
摘要：
与自闭症谱系障碍中社交语言障碍（SLD）相关的特征性语言行为，包括回声性重复、代词位移和刻板媒体引用，在自发对话中基本不存在，仅在特定对话条件下出现。在结构化临床评估中，这种延迟意味着提问策略选择是决定对话产生多少诊断信息的关键但未被充分重视的因素。大型语言模型（LLMs）能否被引导主动选择系统地揭示这些潜在特征的提问策略，在很大程度上仍未探索。本文提出TPA（思考、计划、询问），一种应用于自闭症诊断观察量表模块4（ADOS-2）语言评估部分的主动式多智能体对话框架，其中医生智能体在选择临床依据策略并生成针对性问题之前，明确推理哪些特征尚未观察到。基于真实ADOS-2临床数据的患者智能体使得无需真实患者参与即可进行可重复评估，并通过三个独立实验验证，确认其对真实患者语言具有足够的保真度。在来自35名患者的484个片段上评估，TPA在所有主要指标上优于六个竞争性对话规划基线，实现了82.1%的SLD特征覆盖率，比训练有素的临床医生进行的真实临床对话自动回放（65.5%）高16.6%，并且每轮诊断效率显著更高（AUCC：0.628 vs. 0.458，绝对增益+0.170）。这些结果表明，主动提问策略选择显著提高了自动化SLD特征评估的效率，对可扩展的AI辅助临床筛查具有直接意义。
英文摘要：
Characteristic linguistic behaviors associated with Social Language Disorder (SLD) in autism spectrum disorder, including echoic repetition, pronoun displacement, and stereotyped media quoting, are largely absent from spontaneous conversation and only emerge under specific conversational conditions. In structured clinical assessments, this latency means that questioning strategy selection is a critical yet underappreciated determinant of how much diagnostic information a conversation yields. Whether large language models (LLMs) can be guided to proactively select questioning strategies that systematically surface these latent traits remains largely unexplored. Here we present TPA (Think, Plan, Ask), a proactive multi-agent dialogue framework applied to the language assessment component of the Autism Diagnostic Observation Schedule Module 4 (ADOS-2), in which a doctor agent explicitly reasons about which traits remain unobserved before selecting a clinically grounded strategy and generating a targeted question. A patient agent grounded in real ADOS-2 clinical data enables reproducible evaluation without real patient participation, validated across three independent experiments confirming adequate fidelity to real patient language. Evaluated on 484 episodes from 35 patients, TPA outperforms six competitive dialogue planning baselines across all primary metrics, achieving 82.1% SLD trait coverage, 16.6% higher than automated replay of real clinical dialogues conducted by trained clinicians (65.5%), with substantially greater per-turn diagnostic efficiency (AUCC: 0.628 vs. 0.458, absolute gain +0.170). These results demonstrate that proactive questioning strategy selection substantially improves the efficiency of automated SLD trait assessment, with direct implications for scalable AI-assisted clinical screening.
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。
