8 papers
When More Objectives Make Identification Easier: The Role of Preferences and Feedback
Bo Xue, Ji Cheng, Yuanyu Wan +1
Best-arm identification (BAI) aims to identify the optimal arm using as few samples as possible. While most existing work focuses on a single objective, many real-world application…
Few-for-Many Best-Arm Identification in Multi-Objective Bandits
Bo Xue, Yilu Liu, Haodong Jing +3
Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in a multi-o…
Test-Time Scaling via Budgeted Multi-Attribute Verification
Bo Xue, Ji Cheng, Shen-Huan Lyu +2
Verifying LLM-generated answers under a shared computational budget requires jointly deciding which candidates to inspect and which verification attributes to evaluate. We formulat…
Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluation
Bo Xue, Zhi Hong, Jiayi Li +3
Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives. In this paper, we formulate…
Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits
Bo Xue, Ji Cheng, Haodong Jing +2
This paper studies generalized low-rank matrix bandits with multiple prioritized objectives. At each round, the learner selects a matrix-valued arm and observes a vector-valued rew…
Parametric Pareto Set Learning for Expensive Multi-Objective Optimization
Ji Cheng, Bo Xue, Qingfu Zhang
Parametric multi-objective optimization (PMO) addresses the challenge of solving an infinite family of multi-objective optimization problems, where optimal solutions must adapt to…
Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
Bo Xue, Yuanyu Wan, Zhichao Lu +1
In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In th…
Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories
Dake Bu, Wei Huang, Andi Han +5
Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (…