Paper Detail
Jie Mao, Pingchen Lu, Xiangyi Wang, Hengquan Huang, Shuang Qiu, Min Zhang, Zhongxiang Dai
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@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},
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 },
url = {https://huggingface.co/papers/2610.24385},
keywords = {LLM agents, persona selection, binary comparisons, neural dueling-bandit, IDS-inspired, Bradley-Terry, similarity-weighted warm starts, query-conditioned neural utility model, code available, huggingface daily},
eprint = {2610.24385},
archiveprefix = {arXiv},
}
{}