Simulating nuanced user experiences within complex interactive search systems poses distinct challenge for traditional methodologies, which often rely on static user proxies or, more recently, on standalone large language model (LLM) agents that may lack deep, verifiable grounding. The true dynamism and personalization inherent in human-computer interaction demand a more integrated approach. This work introduces UXSim, a novel framework that integrates both approaches. It leverages grounded data from traditional simulators to inform and constrain the reasoning of an adaptive LLM agent. This synthesis enables more accurate and dynamic simulations of user behavior while also providing a pathway for the explainable validation of the underlying cognitive processes.

翻译：在复杂交互式搜索系统中模拟细微的用户体验，对传统方法构成了独特挑战。这些方法通常依赖于静态用户代理，或近期更多采用独立的大型语言模型（LLM）智能体，但后者可能缺乏深入且可验证的基础。人机交互中固有的真实动态性与个性化需求，要求一种更为整合的研究路径。本研究提出UXSim这一创新框架，它融合了上述两种方法。该框架利用传统仿真器提供的具象化数据，为自适应LLM智能体的推理过程提供信息输入与约束条件。这种综合方法不仅实现了更精准、动态的用户行为仿真，同时为底层认知过程的可解释性验证提供了可行路径。