# What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework

arXiv: https://arxiv.org/abs/2609.12746 · HTML: https://mlsanity.com/paper/2609.12746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 34)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [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)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [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)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes](https://mlsanity.com/paper/2412.19260/) (2024)
- [A Survey on Semantic Parsing](https://mlsanity.com/paper/1812.00978/) (2018)
- [Robust Text-to-SQL Generation with Execution-Guided Decoding](https://mlsanity.com/paper/1807.03100/) (2018)
- [ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration](https://mlsanity.com/paper/2502.00675/) (2025)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities](https://mlsanity.com/paper/2505.20099/) (2025)
- [Text2Cypher: Bridging Natural Language and Graph Databases](https://mlsanity.com/paper/2412.10064/) (2024)
- [ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback](https://mlsanity.com/paper/2503.19988/) (2025)
- [A Universal Question-Answering Platform for Knowledge Graphs](https://mlsanity.com/paper/2303.00595/) (2023)
- [ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects](https://mlsanity.com/paper/2505.17231/) (2025)
- [Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework](https://mlsanity.com/paper/2412.12612/) (2024)
- [DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching](https://mlsanity.com/paper/2602.06039/) (2026)
- [ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement](https://mlsanity.com/paper/2504.20434/) (2025)
- [S2CTrans: Building a bridge from SPARQL to Cypher](https://mlsanity.com/paper/2304.00531/) (2023)
- [Enhancing Text2Cypher with Schema Filtering](https://mlsanity.com/paper/2505.05118/) (2025)

## Abstract (arXiv)

Agentic pipelines for structured-query generation are rapidly expanding, but it is unclear which part of the loop produces the gain. We use LAST-CQ -- a five-agent, training-free, execution-grounded Text-to-Cypher framework -- as an instrumented testbed, running three counterfactuals over 2,471 live-database queries and six backbones spanning three vendor scale tiers. Removing correction is worth between 3.1% aggregate execution-BLEU against the single-pass system and 12.3% against a no-refinement counterfactual (up to 80.7% for the weakest backbone). Replacing schema-grounded, LLM-synthesised feedback with raw database error strings costs almost nothing (20.9% vs. 19.9% naive exact match; <0.2% end-to-end; equivalent within ± 0.075 set-F1 by two one-sided tests). Spending the same call budget on parallel sampling degrades quality by 10-11%. What works is detecting failure and routing it to a retry, not the feedback sophistication or number of samples. LAST-CQ itself recovers 91.7% of queries that fail under single-pass generation, while a query that succeeds first time still costs exactly one LLM call. We also show that n-gram overlap on serialised results is not a bound in either direction: it over-scores against set equivalence on 65.9% of results while under-scoring against judged semantics. Finally, we calibrate our LLM judge against blind human labels and find it optimistic by 9 points.