# BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions

arXiv: https://arxiv.org/abs/2510.05318 · HTML: https://mlsanity.com/paper/2510.05318/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 92 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 30 of 65)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI](https://mlsanity.com/paper/2411.04872/) (2024)
- [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://mlsanity.com/paper/2306.14898/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases](https://mlsanity.com/paper/1909.05378/) (2019)
- [CHESS: Contextual Harnessing for Efficient SQL Synthesis](https://mlsanity.com/paper/2405.16755/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [SParC: Cross-Domain Semantic Parsing in Context](https://mlsanity.com/paper/1906.02285/) (2019)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation](https://mlsanity.com/paper/2405.07467/) (2024)

## Built on by (most cited first, 19 of 19)

- [DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle](https://mlsanity.com/paper/2512.04324/) (2025)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain](https://mlsanity.com/paper/2510.07309/) (2025)
- [Reasoning about Intent for Ambiguous Requests](https://mlsanity.com/paper/2511.10453/) (2025)
- [Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents](https://mlsanity.com/paper/2606.00547/) (2026)
- [SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation](https://mlsanity.com/paper/2603.16161/) (2026)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems](https://mlsanity.com/paper/2604.22313/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [Benchmarking Text-to-Python against Text-to-SQL: The Impact of Explicit Logic and Ambiguity](https://mlsanity.com/paper/2601.15728/) (2026)
- [DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios](https://mlsanity.com/paper/2604.25914/) (2026)
- [BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL](https://mlsanity.com/paper/2608.02876/) (2026)
- [Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent](https://mlsanity.com/paper/2609.38604/) (2026)
- [Can AI autonomously build, operate, and use the entire data stack?](https://mlsanity.com/paper/2512.07926/) (2025)
- [Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study](https://mlsanity.com/paper/2605.26394/) (2026)
- [Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents](https://mlsanity.com/paper/2606.19319/) (2026)
- [PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming](https://mlsanity.com/paper/2608.15931/) (2026)
- [ARCS: Towards Precise Text-to-SQL via Structured Disambiguation](https://mlsanity.com/paper/2610.09396/) (2026)
- [HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments](https://mlsanity.com/paper/2610.12274/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance on single-turn text-to-SQL tasks, but real-world database applications predominantly require multi-turn interactions to handle ambiguous queries, execution errors, and evolving user requirements. Existing multi-turn benchmarks fall short by treating conversation histories as static context or limiting evaluation to read-only operations, failing to reflect production-grade database assistant challenges. We introduce BIRD-INTERACT, a benchmark that restores this realism through: (1) a comprehensive interaction environment coupling each database with a hierarchical knowledge base, metadata files, and a function-driven user simulator, enabling models to solicit clarifications, retrieve knowledge, and recover from errors without human supervision; (2) two evaluation settings consisting of a pre-defined conversational protocol (c-Interact) and an open-ended agentic setting (a-Interact) where models autonomously decide when to query the user simulator or explore the environment; (3) a challenging task suite covering the full CRUD spectrum for business-intelligence and operational use cases, guarded by executable test cases. Each task features ambiguous and follow-up sub-tasks requiring dynamic interaction. The suite comprises BIRD-INTERACT-FULL (600 tasks, up to 11,796 interactions) for comprehensive performance assessment, and BIRD-INTERACT-LITE (300 tasks with simplified databases) for detailed behavioral analysis and rapid method development. Our empirical results highlight BIRD-INTERACT's difficulty: GPT-5 completes only 8.67% of tasks in c-Interact and 17.00% in a-Interact. Analysis via memory grafting and Interaction Test-time Scaling validates the importance of effective interaction for complex, dynamic text-to-SQL tasks.