arXiv cs.AI· Jie Mao, Pingchen Lu, Xiangyi Wang, Hengquan Huang, Shuang Qiu, Min Zhang, Zhongxiang Dai·· 3 小时前AI 评分28
ID-TAP：面向测试时 Agent 个性化的信息导向对决选择框架
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
AI 导读
arXiv 论文提出 ID-TAP，一种受 IDS 启发的神经 dueling-bandit 框架，用于大离散个性化空间下的测试时 LLM Agent 个性化。该框架结合查询条件神经效用模型与轻量 Bradley-Terry 探索器，通过相似度加权热启动跨查询迁移比较证据。在七个用户条件生成 benchmark、固定十轮比较预算下，ID-TAP 取得所评估基线中最强的总体表现。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.24385 [cs.AI] |
| (or arXiv:2610.24385v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.24385 arXiv-issued DOI via DataCite |
Submission history
From: Jie Mao [view email]
[v1]
Sat, 17 Oct 2026 02:40:47 UTC (304 KB)
[v2]
Fri, 23 Oct 2026 08:14:56 UTC (304 KB)
来源：arXiv cs.AI · arxiv.org