# CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment

arXiv: https://arxiv.org/abs/2606.04645 · HTML: https://mlsanity.com/paper/2606.04645/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [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)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [A Survey on Employing Large Language Models for Text-to-SQL Tasks](https://mlsanity.com/paper/2407.15186/) (2024)
- [Knowledge Graph-Guided Retrieval Augmented Generation](https://mlsanity.com/paper/2502.06864/) (2025)
- [Robust Text-to-SQL Generation with Execution-Guided Decoding](https://mlsanity.com/paper/1807.03100/) (2018)
- [Text2Cypher: Bridging Natural Language and Graph Databases](https://mlsanity.com/paper/2412.10064/) (2024)
- [SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task](https://mlsanity.com/paper/2406.10710/) (2024)
- [CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era](https://mlsanity.com/paper/2412.18702/) (2024)
- [A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges](https://mlsanity.com/paper/2412.05208/) (2024)
- [AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data](https://mlsanity.com/paper/2410.11531/) (2024)
- [Enhancing Text2Cypher with Schema Filtering](https://mlsanity.com/paper/2505.05118/) (2025)
- [Text2Cypher Across Languages: Evaluating and Finetuning LLMs](https://mlsanity.com/paper/2506.21445/) (2025)
- [Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2511.20940/) (2025)
- [RetrySQL: text-to-SQL training with retry data for self-correcting query generation](https://mlsanity.com/paper/2507.02529/) (2025)
- [Self-Correction Distillation for Structured Data Question Answering](https://mlsanity.com/paper/2511.07998/) (2025)
- [Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL](https://mlsanity.com/paper/2512.22364/) (2025)
- [Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering](https://mlsanity.com/paper/2605.10318/) (2026)

## Built on by (most cited first, 1 of 1)

- [What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework](https://mlsanity.com/paper/2609.12746/) (2026)

## Abstract (arXiv)

Language models acting as agents over knowledge graphs generate Cypher queries that fail structurally (crashing at the database) or semantically (executing but returning wrong results). We place a pre-execution gate between query generation and a production Neo4j database. The gate validates structure through a four-backend chain culminating in execution against a mirror graph at 5.6 ms median latency. Structurally broken queries are routed to a corrector that iterates structured error feedback through a language model. On seven CypherBench schemas (2348 questions, ACL 2025) the pipeline maintains generation accuracy on every model tested, confirming it operates as a safe defensive layer. The corrector achieves 81% to 95% success across five models (mean 89%). On a template-generated corpus across nine schemas the gate catches 100% of parse errors, 100% of constraint violations, and 100% of schema-reference errors in path queries with labelled endpoints, at zero false positives across 1135 queries. Property sibling-swaps where the substituted name is valid on the target label score 0%, marking the formal boundary where structural validation ends and semantic validation must begin. A planner-based cost gate flags catastrophic plan structures before execution.