Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
cs.MA, cs.AI, cs.DB
Submitted: 2026-06-17
Updated: 2026-08-31
Project page: https://bird-critic.github.io
Terminology
Sources
- AgentNLQ: A General-Purpose Agent for Natural Language to SQL
- APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
- RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
- Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL
- ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
- DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation
- A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL
- Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
- AgentSM: Semantic Memory for Agentic Text-to-SQL
- Coding Agents with Multimodal Browsing are Generalist Problem Solvers
- TableGPT2: A Large Multimodal Model with Tabular Data Integration
- CHESS: Contextual Harnessing for Efficient SQL Synthesis
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
- Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
- Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language
- Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
- AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
- OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment
- MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery
- StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning