4 papers
How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
Longju Bai, Zhemin Huang, Xingyao Wang +5
The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of t…
SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
Emil Biju, Shayan Talaei, Zhemin Huang +3
Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the…
Hawkeye:Efficient Reasoning with Model Collaboration
Jianshu She, Zhuohao Li, Zhemin Huang +4
Chain-of-Thought (CoT) reasoning has demonstrated remarkable effectiveness in enhancing the reasoning abilities of large language models (LLMs). However, its efficiency remains a c…
Chengyu-Bench: Benchmarking Large Language Models for Chinese Idiom Understanding and Use
Yicheng Fu, Zhemin Huang, Liuxin Yang +2
Chinese idioms (Chengyu) are concise four-character expressions steeped in history and culture, whose literal translations often fail to capture their full meaning. This complexity…