Ruoxi Sun

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training

From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models