4 papers
Incentive Effects of a Cut-Off Score: Optimal Contest Design with Transparent Pre-Selection
Hanbing Liu, Ningyuan Li, Weian Li +2
Shortlisting is a common and effective method for pre-selecting participants in competitive settings. To ensure fairness, a cut-off score is typically announced, allowing only cont…
Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use
Hanbing Liu, Chunhao Tian, Nan An +4
We study budget-constrained tool-augmented agents, where a large language model must solve multi-step tasks by invoking external tools under a strict monetary budget. We formalize…
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
Hanbing Liu, Haoyang Li, Xiaokang Zhang +5
Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it…
Optimal Contest Design with Entry Restriction
Hanbing Liu, Ningyuan Li, Weian Li +2
This paper explores the design of contests involving contestants, focusing on how the designer decides on the number of contestants allowed and the prize structure with a fixed…