@article{userpreferencemodelingforconversationall,
  title = {User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction},
  author = {Yuren Hao and Shuhaib Mehri and ChengXiang Zhai and Dilek Hakkani-Tür},
  year = {2026},
  eprint = {2603.20939},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.20939},
}