CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 3 Jun 2026.
Builds on
23 of 35 references.
References · 23
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2023Teaching Large Language Models to Self-Debugcited by 963
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
- 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
- 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
- 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
- 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
- 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 57
- 2018Robust Text-to-SQL Generation with Execution-Guided Decodingcited by 51
- 2024Text2Cypher: Bridging Natural Language and Graph Databasescited by 30
11 more
- 2024SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Taskcited by 19
- 2024CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Eracited by 13
- 2024A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challengescited by 9
- 2024AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Datacited by 8
- 2025Enhancing Text2Cypher with Schema Filteringcited by 6
- 2025Text2Cypher Across Languages: Evaluating and Finetuning LLMscited by 3
- 2025Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphscited by 3
- 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generationcited by 2
- 2025Self-Correction Distillation for Structured Data Question Answeringcited by 2
- 2025Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQLcited by 2
- 2026Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filteringcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.