UXSim: Towards a Hybrid User Search Simulation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910035405176832 |
|---|---|
| author | Zerhoudi, Saber Granitzer, Michael |
| author_facet | Zerhoudi, Saber Granitzer, Michael |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_24241 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UXSim: Towards a Hybrid User Search Simulation Zerhoudi, Saber Granitzer, Michael Information Retrieval Human-Computer Interaction 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. |
| title | UXSim: Towards a Hybrid User Search Simulation |
| topic | Information Retrieval Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.24241 |