CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment

• URL: http://arxiv.org/abs/2606.04645v1
• Date: Wed, 03 Jun 2026 09:13:05 GMT
• Title: CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
• Abstract summary: We place a pre-execution gate between query generation and a production Neo4j database.<n>The gate validates structure through a four-backend chain culminating in execution against a mirror graph at 5.6 ms median latency.<n>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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SilentProbe: Measuring Silent Failure in Production APIs Used as Agent Tools [0.0]
  We find that machine-checkable constraints yielded an honest error in 111 of 111 cases, prose-only constraints failed silently in 44 of 61.<n>A vocabulary that the description merely exemplifies was missed by every model on 88 of 88 attempts, while vocabularies written out in full were used correctly 88 to 91% of the time.
  arXiv  Detail & Related papers  (2026-08-29T07:07:28Z)
• From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing [50.70862449978062]
  Recent documents achieve table TEDS scores above 93 on OmniDocBench v1.6, yet community feedback and our audit reveal persistent failures on complex real-world tables.<n>To quantify this gap, we introduce TableParseMap, a diagnostic benchmark of 916 real-world tables organized into five challenging scenarios and nine failure types.
  arXiv  Detail & Related papers  (2026-08-10T16:59:30Z)
• Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline [0.0]
  This paper introduces WarehouseBench, 400 frozen tasks over two synthetic warehouses in which roughly half the correct responses are a clarification, an abstention or a refusal.<n>QueryProof, a 7B agent, uses rules derived from a semantic layer and physical catalog to determine its behaviour.
  arXiv  Detail & Related papers  (2026-08-10T08:14:24Z)
• DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling [0.19116784879310023]
  Deploying natural-language interfaces over enterprise O fails scale because schemagraph fails to scale at scale.<n>We present DRL, a safe pipeline interposing between front-ends backends.<n>We evaluate DRL onop, a 1,000 scaling model, and an enterprise schema-linked NL2 taxonomy.<n>GPT-4o, Claude Sonnet 4.5, and Gemini 2.5 Flash achieve 52.9%, 54.5%, and 52.1% execution match under a corrected evaluation harness.
  arXiv  Detail & Related papers  (2026-07-23T18:01:11Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics [0.10210859604701106]
  Modern warehouses contain thousands of tables, abbreviated columns, informal metrics, hidden join conventions, and permission boundaries not captured by raw table names.<n>We introduce Enterprise-First Retrieval, a retrieval layer that embeds catalog metadata rather than warehouse rows.<n>The system indexes five typed catalog objects, tables, columns, metrics, relationships, and query history, using object-specific text templates.
  arXiv  Detail & Related papers  (2026-06-23T02:20:36Z)
• CAPER: Clause-Aligned Process Supervision for Text-to-SQL [11.286563956844946]
  We propose CAPER, which automatically derives clause-level supervision via counterfactual intervention on the SQL abstract syntax tree.<n>The resulting data is used to train CAPER-9B, a lightweight Clause-boundary feedback for policy optimization and candidate verification.<n> Experiments on BIRD and Spider show that clause-aligned supervision not only improves execution accuracy, achieving up to a 15.3% relative EX improvement over GPT-5.4, but also strengthens failure-localization capability, reaching 84.53% accuracy and 90.60% MRR on held-out failures.
  arXiv  Detail & Related papers  (2026-06-02T08:35:40Z)
• DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analytics [7.702420465302456]
  DisasterLex is a knowledge-graph-mediated framework that inserts an Expert Knowledge Graph (EKG) of curated concepts and typed causal edges between the user query and the database.<n>We instantiate it on a disaster-analytics database with an EKG of 107 concepts, 117 causal edges, and 52 concept-to-table links.<n>On all seven base models spanning proprietary and open-weight families, DisasterLex beats four state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-28T20:13:02Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models [0.0]
  LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures.<n>We benchmark three frontier LLMs on 100 natural-language questions over the Cleaned Contoso Retail dataset in ClickHouse.
  arXiv  Detail & Related papers  (2026-04-28T02:53:23Z)
• ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement [57.98138819417949]
  We propose ErrorLLM, a framework that explicitly models text-to- querying.<n>We show that ErrorLLM achieves the most significant improvements over backbone initial generation.<n>ErrorLLM addresses both sides by high detection F1 score while maintaining refinement effectiveness.
  arXiv  Detail & Related papers  (2026-03-04T05:27:20Z)
• Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims [0.609170287691728]
  EviBound is an evidence-bound execution framework that eliminates false claims through dual governance gates.<n>The pre-execution Approval Gate validates acceptance criteria schemas before code runs.<n>The post-execution Verification Gate validates artifacts via MLflow API queries.
  arXiv  Detail & Related papers  (2025-10-28T17:47:13Z)
• SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code [46.20378145112059]
  Post-hoc repair pipelines detect such faults only after execution.<n>We present SemGuard, a semantic-evaluator-driven framework that performs real-time, line-level semantic supervision.
  arXiv  Detail & Related papers  (2025-09-29T09:21:32Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• Analyzing the Effectiveness of Large Language Models on Text-to-SQL Synthesis [4.412170175171256]
  This study investigates various approaches to using Large Language Models for Text-to- program synthesis. The goal was to input a natural language question along with the database schema and output the correct SELECT query.
  arXiv  Detail & Related papers  (2024-01-22T22:05:42Z)
• PRover: Proof Generation for Interpretable Reasoning over Rules [81.40404921232192]
  We propose a transformer-based model that answers binary questions over rule-bases and generates the corresponding proofs. Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm. We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation.
  arXiv  Detail & Related papers  (2020-10-06T15:47:53Z)
• Improving One-stage Visual Grounding by Recursive Sub-query Construction [102.47477888060801]
  We improve one-stage visual grounding by addressing current limitations on grounding long and complex queries. We show our new one-stage method obtains 5.0%, 4.5%, 7.5%, 12.8% absolute improvements over the state-of-the-art one-stage baseline.
  arXiv  Detail & Related papers  (2020-08-03T17:43:30Z)
• TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task [80.38130122127882]
  TACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE) In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.
  arXiv  Detail & Related papers  (2020-04-30T15:07:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.