融合传统仿真与大模型，实现更真实可解释的用户搜索行为模拟
UXSim: Towards a Hybrid User Search Simulation
- 用传统仿真数据约束大模型推理，实现动态行为建模
- 支持可解释的认知过程验证，提升模拟可信度
- 适合交互系统设计、人机协同研究者使用
在复杂交互式搜索系统中模拟用户行为面临挑战，传统方法依赖静态用户代理，近期方法虽采用独立的大语言模型（LLM）代理，但可能缺乏深层可验证的依据。人类-计算机交互中的真实动态性与个性化要求更集成的方法。本文提出UXSim框架，融合传统仿真生成的接地数据与自适应大语言模型代理的推理能力。该整合使用户行为模拟更准确且动态，并为底层认知过程提供可解释的验证路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。