The paper introduces Conversational Generalized Linear Bandits with Hybrid Feedback, a framework that blends absolute item rewards (such as clicks or ratings) with relative key‑term comparisons. It proposes the Conversational UCB with Hybrid Feedback (HyConUCB) algorithm, which builds unified confidence bounds from heterogeneous feedback and adaptively selects key‑term comparisons to balance information gain and directional coverage. A refined regret analysis shows that HyConUCB outperforms reward‑only and dueling‑only baselines, and experiments on synthetic and real‑world data confirm its effectiveness.
By Yurui Zou, Qirun Zeng, Jinhang Zuo
arXiv:2607. 09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing.
By Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan
arXiv:2602. 02061v2 Announce Type: replace Abstract: Explosive demands for LLMs often cause user queries to accumulate in server queues, requiring efficient routing (query-LLM matching) and scheduling (query prioritization) mechanisms.
By Seoungbin Bae, Junyoung Son, Dabeen Lee
The paper investigates best‑arm identification (BAI) in multi‑objective bandits, showing that additional objectives can actually reduce the number of samples needed. For Gaussian bandits, a characteristic‑time lower bound is derived that applies uniformly across preference orders, and explicit comparisons under Pareto, linear, and lexicographic preferences reveal that a larger optimal set can be identified with fewer samples, that the benefit of vector feedback depends on the preference, and that multi‑objective BAI can outperform the easiest single‑objective case. The authors also introduce Order‑Aware Track‑and‑Stop (OATS), an algorithm that achieves the lower bound while guaranteeing correctness at any desired confidence level.
By Bo Xue, Ji Cheng, Yuanyu Wan, Shuang Qiu
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.
By Jiahao Zeng, Ming Tang, Ningning Ding
PEARL is a neural contextual bandit algorithm that selectively forgets only the dimensions of user preferences that have drifted, by reversing the Gram matrix update along feature directions where predictions are surprisingly wrong. The method achieves lower cumulative regret that scales with the number of shifted users rather than the entire population, and outperforms greedy, sliding‑window, and discounted baselines on the PRISM personalized LLM response selection benchmark, improving scores by 2.5 to 4.0 points over the best neural bandit baseline.
By Rashmi Gangadharaiah, Balakrishnan Narayanaswamy
arXiv:2606. 01382v1 Announce Type: cross Abstract: Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward.
By Tianlong Nan, Xiaopeng Li, Christian Kroer, Tianyi Lin
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2605. 04267v2 Announce Type: replace Abstract: Interactive multi-objective optimization systems face a budget allocation dilemma: one can spend resources on expensive objective evaluations or on eliciting decision-maker preferences that identify the relevant region of the Pareto set.
By Florian A. D. Burnat
arXiv:2501. 07761v2 Announce Type: replace-cross Abstract: Increasingly, recommender systems are tasked with improving users' long-term satisfaction.
By Kelly W. Zhang, Thomas Baldwin-McDonald, Kamil Ciosek, Lucas Maystre, Daniel Russo
arXiv:2512. 00517v3 Announce Type: replace-cross Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings.
By Eliabelle Mauduit, Elo\"ise Berthier, Andrea Simonetto
arXiv:2602. 17976v2 Announce Type: replace-cross Abstract: In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible.
By Alessio Russo, Yin-Ching Lee, Ryan Welch, Aldo Pacchiano