The paper introduces ID‑TAP, a neural dueling‑bandit framework that personalizes large‑language‑model agents at test time by selecting personas through binary comparisons of candidate responses. It combines a query‑conditioned neural utility model with a lightweight Bradley‑Terry explorer, and uses similarity‑weighted warm starts to transfer evidence across related queries. Experiments on seven user‑conditioned generation benchmarks show that ID‑TAP outperforms baselines within a ten‑round comparison budget, demonstrating the effectiveness of information‑directed challenger selection for persona adaptation.
arXiv:2509. 24696v2 Announce Type: replace-cross Abstract: Personalizing large language models (LLMs) to individual user preferences is a critical step beyond generating generically helpful responses.
arXiv:2605. 00696v2 Announce Type: replace-cross Abstract: We study adaptive querying for learning user-dependent quantities of interest, such as responses to held-out items and psychometric indicators, within tight query budgets.
arXiv:2609.36488v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong performance on complex web navigation tasks, yet they remain brittle in real-world settings...
arXiv:2606. 00846v1 Announce Type: new Abstract: Users increasingly face the challenge of selecting an appropriate LLM for a given task from a rapidly growing pool of LLMs, each with distinct but often opaque latent properties.
arXiv:2605.12894v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are uncle...
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
arXiv:2606. 08410v1 Announce Type: cross Abstract: Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives.
arXiv:2604. 05379v2 Announce Type: replace-cross Abstract: The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences.
arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.
arXiv:2609.37800v1 Announce Type: cross Abstract: Many recommender services repeatedly encounter cold-start cohorts, where new users arrive with little or no interaction history. This creates two cha...
The paper introduces a method for creating query‑specific rubrics for DeepResearch‑style long‑form report generation by training rubric generators with reinforcement learning. It builds a dataset of queries annotated with human preferences, then uses a hybrid reward that includes preference consistency, format validity, and LLM‑based rubric evaluation. The learned rubrics outperform generic or manually constructed alternatives in distinguishing preferred reports and, when used as rewards, improve performance of both single‑agent and multi‑agent DeepResearch systems.
The paper introduces a simulation framework that uses large language model (LLM) agents conditioned on data‑driven personas to predict A/B test outcomes. These personas are built from anonymized user behavioral patterns, engagement signals, and inferred demographics, offering a more realistic population model than synthetic or rule‑based personas. The authors evaluate question design, persona data source, behavioral depth versus diversity, and population subsampling, achieving 0.75–0.90 directional accuracy on 40 real A/B tests.