3 papers
cs.AI2026
Knowing How to Edit: Reliable Evaluation Signals for Diagnosing and Optimizing Prompts at Query Level
Ke Chen, Yifeng Wang, Hassan Almosapeeh +1
Prompt optimization has become a central mechanism for eliciting strong performance from LLMs, and recent work has made substantial progress by proposing diverse prompt evaluation…
cs.DB2025
RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
Zui Chen, Han Li, Xinhao Zhang +12
We present RubikSQL, a novel NL2SQL system designed to address key challenges in real-world enterprise-level NL2SQL, such as implicit intents and domain-specific terminology. Rubik…
cs.AI2024
Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas
Xiang Hu, Hongyu Fu, Jinge Wang +7
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produc…