10 papers
Terminal Agents: A Survey of AI Agents in Command-Line Environments
Yi Bin, Xiaoyang Yuan, Haoxi Zeng +9
Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use res…
Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs
Ruixuan Huang, Jinyuan Shi, Hantao Huang +5
We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8B dense backbone, we continu…
Provable Joint Decontamination for Benchmarking Multiple Large Language Models
Zhenlong Liu, Hao Zeng, Hongxin Wei
Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performa…
Improving Backward Conformal Prediction via Non-Conformity Score Transformation
Junxian Liu, Hao Zeng, Hongxin Wei
Conformal Prediction (CP) provides a statistical framework for uncertainty quantification that constructs prediction sets with coverage guarantees. While CP yields uncontrolled pre…
An Interpretable and Scalable Framework for Evaluating Large Language Models
Xinhao Qu, Qiang Heng, Hao Zeng +1
Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the inherent stochasticity of LLM…
RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
Sai Hao, Hao Zeng, Hongxin Wei +1
Efficiently routing queries to the optimal large language model (LLM) is crucial for optimizing the cost-performance trade-off in multi-model systems. However, most existing router…