5 papers
TQA-Bench: Evaluating LLMs for Multi-Table Question Answering
Zipeng Qiu, Chenyue Li, You Peng +3
The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question answering (QA) over complicated…
HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
You Peng, Youhe Jiang, Wenshuang Li +5
Agentic LLM applications increasingly execute user requests as multi-step workflows involving planning, tool use, branching, refinement, and synthesis. In such settings, users expe…
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Youhe Jiang, Ran Yan, You Peng +4
Modern Large Language Model (LLM) serving operates in highly volatile environments characterized by severe runtime dynamics, such as workload fluctuations and elastic cluster autos…
HEXGEN-FLOW: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL
You Peng, Youhe Jiang, Wenqi Jiang +2
Recent advances in agentic large language models (LLMs) have substantially improved Text-to-SQL, enabling users without database expertise to query databases intuitively. However,…
Zero-Indexing Internet Search Augmented Generation for Large Language Models
Guangxin He, Zonghong Dai, Jiangcheng Zhu +6
Retrieval augmented generation has emerged as an effective method to enhance large language model performance. This approach typically relies on an internal retrieval module that u…