Theory of Mind (ToM) reasoning with Large Language Models (LLMs) requires inferring how people's implicit, evolving beliefs shape what they seek and how they act under uncertainty -- especially in high-stakes settings such as disaster response, emergency medicine, and human-in-the-loop autonomy. Prior approaches either prompt LLMs directly or use latent-state models that treat beliefs as static and independent, often producing incoherent mental models over time and weak reasoning in dynamic contexts. We introduce a structured cognitive trajectory model for LLM-based ToM that represents mental state as a dynamic belief graph, jointly inferring latent beliefs, learning their time-varying dependencies, and linking belief evolution to information seeking and decisions. Our model contributes (i) a novel projection from textualized probabilistic statements to consistent probabilistic graphical model updates, (ii) an energy-based factor graph representation of belief interdependencies, and (iii) an ELBO-based objective that captures belief accumulation and delayed decisions. Across multiple real-world disaster evacuation datasets, our model significantly improves action prediction and recovers interpretable belief trajectories consistent with human reasoning, providing a principled module for augmenting LLMs with ToM in high-uncertainty environment. https://anonymous.4open.science/r/ICML_submission-6373/

翻译：心理理论（ToM）推理与大语言模型（LLM）的结合需要推断人们隐含且不断演变的信念如何塑造他们在不确定性下的行为——尤其在灾后响应、急诊医学和人机协同等高风险场景中。现有方法要么直接提示LLM，要么使用将信念视为静态且独立的潜状态模型，这常导致随时间推移产生不一致的心理模型，以及在动态情境中推理能力薄弱。我们提出一种基于LLM的结构化认知轨迹模型，将心理状态表示为动态信念图，共同推断潜在信念、学习其随时间变化的依赖关系，并将信念演变与信息寻求和决策联系起来。该模型的贡献包括：（i）一种从文本化概率陈述到一致性概率图模型更新的新颖投影方法，（ii）一种基于能量的信念依赖关系因子图表示，以及（iii）一种捕捉信念累积与延迟决策的基于ELBO的目标函数。在多个真实灾难疏散数据集上，我们的模型显著提升了行动预测性能，并恢复了与人类推理一致的可解释信念轨迹，为在高不确定性环境中增强LLM的ToM能力提供了理论化模块。https://anonymous.4open.science/r/ICML_submission-6373/