| title | Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization |
|---|---|
| authors | Jie Mao, Pingchen Lu, Xiangyi Wang, Hengquan Huang, Shuang Qiu, Min Zhang, Zhongxiang Dai |
| date | 2026-10-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.24385 |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparisons between candidate responses as the online signal. We present ID-TAP, a scalable, IDS-inspired neural dueling-bandit framework for large discrete persona spaces. ID-TAP combines a query-conditioned neural utility model with a lightweight Bradley-Terry explorer, and transfers comparison evidence across related queries through similarity-weighted warm starts. The neural model shares statistical strength across queries while preserving query-specific scores, and efficient BT updates score hypothetical challengers. Across seven user-conditioned generation benchmarks under reference- and model-based preference simulators, ID-TAP achieves the strongest aggregate performance among the evaluated baselines within a fixed ten-round comparison budget. These results support information-directed challenger selection as an effective design for test-time persona adaptation. |
cite
@misc{mao2026bridging,
title={Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization},
author={Jie Mao and Pingchen Lu and Xiangyi Wang and Hengquan Huang and Shuang Qiu and Min Zhang and Zhongxiang Dai},
year={2026},
eprint={2610.24385},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.24385}
}