ReNL2SQL 2026: 1st International Workshop on Reliable NL2SQL for Enterprise AI Systems
ReNL2SQL 2026 will be held in the Cross-AI Symposium 2026.
Introduction
Natural Language to SQL (NL2SQL) has advanced rapidly with Large Language Models (LLMs), achieving strong performance on benchmarks such as Spider and BIRD. However, these gains have not translated into reliable deployment in real-world enterprise and high-stakes application domains, including finance, healthcare, logistics, and enterprise operations.
A key challenge is a persistent gap between benchmark assumptions and production reality. Existing benchmarks typically assume small, clean, and static schemas; fully specified user intent; limited join complexity; few-database settings; and accuracy-centric evaluation. These simplifications support rapid progress on benchmark metrics but fail to reflect real-world conditions.
In practice, enterprise and domain-specific systems are significantly more complex. They span thousands of evolving, poorly documented tables across distributed cloud platforms, with inconsistent business definitions, strict access controls, and heterogeneous data types. This makes both structure and semantics difficult to navigate, requiring user queries to be translated from high-level intent into grounded schemas, disambiguated metrics, and cost-aware execution plans across multiple systems. Despite strong benchmark performance, real-world deployment often fails due to incorrect joins, hallucinated tables or columns, weak grounding in domain metadata, limited scalability, and a lack of cost and system awareness that can lead to unsafe or overly expensive queries.
Meanwhile, NL2SQL is evolving from single-step query generation into agentic analytics systems that must retrieve and reason over schemas, plan multi-step workflows, interact through clarification, execute and validate SQL, and repair failures while operating under cost, latency, and governance constraints.
This workshop frames NL2SQL as a real-world AI systems challenge at the intersection of foundation models, databases, cloud infrastructure, and agentic reasoning. It positions NL2SQL as a core component of enterprise and high-stakes AI infrastructure and aims to shape a research agenda focused on trustworthy, scalable, cross-aware, and production-ready NL2SQL systems, bridging the gap between benchmark success and real-world impact.
Topics
Enterprise NL2SQL and Foundation Models
- Large-schema reasoning and retrieval
- Metadata-aware query generation
- Semantic-layer & business metric reasoning
Agentic and Conversational Data Systems
- Ambiguous, interactive, & querying
- Agentic AI for data intelligence & query generation
- Human-in-the-loop structured data reasoning
Cross-Systems and Cloud-Scale Analytics
- Cross-table and cross-database reasoning
- Execution-aware & cost-efficient query generation
- Scalable architectures for NL-to-data interfaces
Safety, Reliability, and Governance
- Reliability and failure analysis in NL2SQL systems
- Cost-aware SQL generation
- Security, privacy, & governance for NL data access
- Deployment-driven evaluation metrics
- Runtime optimization and monitoring
Advanced Reasoning and Applications
- Geospatial & complex structured data reasoning
- High-stakes application domains (e.g., finance, healthcare, enterprise BI)
- Robustness under ambiguity, distribution shift, and noisy schemas
Important Dates (AoE)
| Milestone | Cross-AI Archival Paper Deadline | Non-Archival Paper Deadline |
|---|---|---|
| Full/Short Paper Submission | October 26, 2026 | N/A |
| Poster/Demo Paper Submission | November 2, 2026 | November 16, 2026 |
| Abstract Submission | November 2, 2026 | November 16, 2026 |
| Acceptance Notification | November 16, 2026 | November 30, 2026 |
| Camera-Ready Submission | November 30, 2026 | N/A |
| Pre-Recorded Video Submission | November 30, 2026 | November 30, 2026 |
| Author Registration Deadline | December 2, 2026 | December 2, 2026 |
| Cross-AI Symposium 2026 | December 14-16, 2026 |
Archival work submissions for the Cross-AI Symposium must be submitted by the first deadline. Non-archival submissions may be submitted by either deadline.
Submission
All submissions are made through the AirBalloon conference management system and evaluated through a unified process.
1. Unpublished and Unreviewed Papers
Unpublished and unreviewed papers should follow the IEEE conference manuscript template (Overleaf or US Letter), be written in English, submitted as PDF files, and undergo double-blind review.
| Category | Length (including references) |
|---|---|
| Full paper | 8–10 pages |
| Short paper | 5–7 pages |
| Poster paper | 3–4 pages |
| Demo paper | 2–3 pages with a link to a 2-minute demo video |
| Extended Abstract | 1 page |
2. Reviewed but Not Yet Published Papers
For papers previously submitted to major AI/ML/NLP/Computer Vision/Robotics/Signal Processing/Graphics conferences (e.g., NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR, ECCV, AAAI, ICRA, IROS, CoRL, SIGGRAPH, ACM MM, ICASSP, HCI, KDD), please include the original reviews as supplementary material, clearly indicating the conference, along with a separate document summarizing the revisions addressing the reviewers’ comments. This may help expedite the review process.
3. Non-Archival Submissions
Non-archival submissions may include published journal or conference papers, as well as works in progress seeking feedback. All are welcome for presentation at Cross-AI events. For published papers, authors only need to submit an abstract and the original DOI link.
4. E-Posters and Demo Videos
Electronic posters and/or demo videos are optional for all submission types (Full, Short, Poster, Demo, and Non-Archival).
| Category | Description |
|---|---|
| E-Poster | 1-page electronic poster (PDF) |
| Demo Video | up to 2-minute demo video |
5. Pre-Recorded Presentation Videos
Accepted submissions provide a pre-recorded video.
| Category | Presentation | Q&A |
|---|---|---|
| Full paper | 15 minutes | 3 minutes |
| Short paper | 10 minutes | 2 minutes |
| Poster | 6 minutes | 2 minutes |
| Demo | 5 minutes (system description + showcase) | 2 minutes |
| Abstract | 5 minutes | 2 minutes |
Publishing & Registration Requirements
All accepted archival papers will be published in the indexed Cross-AI conference proceedings. At least one author must register for the workshop. Authors may optionally have their papers considered for further publication in an IEEE-published Cross-AI Special Edition in 2027, subject to Cross-AI approval and an additional publication fee.
Media Hosting: Submitted presentation and demo videos, e-posters, audio, and other approved media will be hosted on the conference platform and made openly accessible for three years. Media hosting and open access are included in the Author registration fee.
Cross-AI Group
This group serves as a forum for notices and announcements of interest to the Cross-AI community. This includes news, events, calls for papers, calls for collaborations between academia and industry, dataset releases, employment-related announcements, etc.
Welcome to subscribe to the Cross-AI group.
If you are interested in serving on the workshop program committee or paper reviewing, please apply online.