arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.24241cs.IRcs.HC
收藏

UXSim: 向混合用户搜索模拟迈进

UXSim: Towards a Hybrid User Search Simulation

University of Passau(帕绍大学);IT:U Austria(奥地利信息技术大学)

Saber Zerhoudi, Michael Granitzer

AI总结:

UXSim 通过整合传统模拟器与适应性 LLM 代理,提供更准确的用户行为模拟和可解释的验证方法。

摘要:

在复杂的交互搜索系统中模拟细腻的用户体验对传统方法提出了独特的挑战,这些方法往往依赖静态用户代理或更近期的独立大型语言模型(LLM)代理,这些代理可能缺乏深入且可验证的 grounding。人类与计算机交互中真正的动态性和个性化需求更集成的方法。这项工作引入了UXSim,一种新的框架,整合了这两种方法。它利用传统模拟器的 grounded 数据来指导和约束适应性 LLM 代理的推理。这种合成使用户行为的模拟更加准确和动态,同时为底层认知过程的可解释验证提供了途径。

英文摘要:

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.

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。

↑