arXiv:2606. 23933v1 Announce Type: cross Abstract: We study non-stationary linear contextual bandits where the reward model drifts over time, rendering classical contextual bandit algorithms brittle because historical data becomes systematically biased.
By AmirHossein Naghdi, Ali Baheri
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:2606. 14929v1 Announce Type: cross Abstract: Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models.
By Yan Dai, Negin Golrezaei, Patrick Jaillet
The paper introduces Q-Target Pretrained Transformers (QTPT), a method that replaces supervised behavior cloning with a Bellman-style Q‑target objective for in‑context reinforcement learning. QTPT retains the context‑conditioned Transformer architecture but learns to estimate action values using rewards and transitions from the context, rather than merely imitating offline actions. The authors provide theoretical analysis in stochastic linear bandits and finite‑horizon MDPs, demonstrating improved robustness to weak or suboptimal data, and empirically show gains over supervised pretraining on controlled RL benchmarks and extensions to D4RL Kitchen and AntMaze.
By Yichen Lin, Xuyuan Xiong, Xue Wang, Xiangfu Meng, Mike Mingcheng Wei, Tao Yao
The paper introduces Online Hyperparameter Optimization (OHPO), framing it as an infinitely many‑armed bandit problem over mixed and conditional search spaces. It proposes the IMABO framework, which couples any bandit policy with any oracle for proposing new configurations, and presents IMOSS—a restart‑free anytime policy with provable regret bounds. Experiments show that IMABO, combined with practical oracles such as TPE, an incumbent‑mutation oracle, and a pretrained tabular foundation model, outperforms random search across a range of settings from classical ML models to LLM‑based agents.
By Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
arXiv:2606. 19750v1 Announce Type: cross Abstract: Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization.
By Darrien McKenzie, Nicklas Hansen, Xiaolong Wang