7 papers
QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics
Tianjing Zeng, Yuntao Hong, Zhongjun Ding +17
The paper presents QwenPaw-Data, an autonomous agent system that turns natural‑language requests into end‑to‑end enterprise data analysis workflows by integrating semantic groundin…
AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning
Qingxu Fu, Boyin Liu, Shuchang Tao +5
Training reinforcement learning (RL) policies for large language model (LLM) agents requires optimizing multi-turn trajectories that interact with external environments. Existing t…
SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models
Yin Lin, Tianjing Zeng, Zhongjun Ding +4
Relational databases excel at structured data analysis, but real-world queries increasingly require capabilities beyond standard SQL, such as semantically matching entities across…
AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL
Zhongjun Ding, Yin Lin, Tianjing Zeng +3
Text-to-SQL systems translate natural language questions into SQL queries, providing substantial value for non-expert users. While large language models (LLMs) show promising resul…
Learned Query Optimizer in Alibaba MaxCompute: Challenges, Analysis, and Solutions
Lianggui Weng, Dandan Liu, Wenzhuang Zhu +5
Existing learned query optimizers remain ill-suited to modern distributed, multi-tenant data warehouses due to idealized modeling assumptions and design choices. Using Alibaba's Ma…
BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases
Lianggui Weng, Dandan Liu, Rong Zhu +2
As large language models (LLMs) demonstrate increasingly powerful reasoning and orchestration capabilities, LLM-based agents are rapidly proliferating for complex data-related task…