What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
Ioannis Prokopiou and colleagues (Athens University of Economics and Business and Orfium) ablate a five-agent Text-to-Cypher refinement loop to find which component produces its gains, over 2,471 live-database queries and six backbones.
Ask this paper
Correction matters: Removing correction costs 3.1% aggregate execution-BLEU against a single-pass system and 12.3% against a no-refinement counterfactual, up to 80.7% for the weakest backbone.
Feedback detail does not: Replacing schema-grounded LLM feedback with raw database error strings changes almost nothing (20.9% vs 19.9% exact match), equivalent within 0.075 set-F1.
Sampling hurts: Spending the same call budget on parallel sampling lowers quality by 10% to 11%.
Recovery: LAST-CQ recovers 91.7% of queries that fail single-pass, and a query that succeeds first time still costs one LLM call.
Metric caveats: N-gram overlap over-scores against set equivalence on 65.9% of results, and the LLM judge is 9 points more optimistic than blind human labels.
Abstract
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 $\pm 0.075$ 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.