One paper argues that text-to-MQL evaluation should be built by migrating a text-to-SQL benchmark with access-pattern-aware schema design and data-preserving conversion, rather than by mirroring relational foreign keys into a document store. Another introduces SyntaxBench, a diagnostic benchmark and statistical evaluation framework for character-level reasoning in large language models, with tasks including character counting, letter containment, palindrome detection, edit distance, longest-string selection and the harder index_to_span substring-extraction test.

AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration

Use access-pattern-driven document schemas and verify migration loss, because heuristic SQL-to-MQL conversion can drop up to 25.9% of rows and fails on 6 of 21 BIRD databases.

Document databases such as MongoDB are core infrastructure for modern applications, and natural-language interfaces to them---text-to-MQL---would let non-experts query complex, semi-structured data without mastering the query language. Progress on this task depends on high-quality benchmarks, which are most practically obtained by converting an existing text-to-SQL benchmark to the document setting. Unfortunately, existing efforts rely on heuristics for mechanical conversion: the document schema mirrors the relational foreign-key graph, and each query mirrors its source SQL. As a result in our experiments, these approaches fail to migrate 6 of 21 BIRD databases outright, silently drop up to 25.9% of rows on others, and yield schemas whose ground-truth queries run over an order of magnitude slower as the data scales. We instead propose a conversion pipeline, driven by coding agents with human-in-the-loop verification, that designs each document schema from expected access patterns and rewrites queries to be MongoDB-native. Applying it to BIRD, we build an access-pattern-based text-to-MQL benchmark (AptMQL-Bench). It includes 21 document-oriented databases, 3,186 natural-language requests, and their associated MQL queries---whose databases are migrated from SQLite without data loss and scale efficiently. The strongest model, Claude Opus 4.5, achieves only 57.38% accuracy without external knowledge evidence and 70.34% with it. This indicates that realistic text-to-MQL generation remains challenging.

SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models

Character-level performance depends strongly on tokenization, so benchmark and prompt models on the exact character visibility your production text will have rather than assuming reasoning mode fixes syntax errors.

Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isolated probes and aggregate accuracy. We introduce SyntaxBench, a diagnostic benchmark and statistical evaluation framework for character-level reasoning. It contains five core tasks, character counting, letter containment, palindrome detection, edit distance, and longest-string selection, plus index_to_span, a harder substring-extraction stress test. The five core tasks use paired English and character-length-matched random-string inputs. index_to_span documents share a 200-500 word band and are not character-length matched. All six tasks use zero-, one-, and four-shot prompts. We evaluate eight open-weight models from 2B to 32B parameters across 11 reasoning-mode configurations. The framework reports exact-match and relaxed accuracy, Cohen's kappa, paired McNemar tests with odds ratios, bootstrap confidence intervals, Kendall's tau, class-conditional metrics, tokenization analysis, and multiple-comparison-corrected tests. Three findings stand out. First, tokenization shapes accuracy: random strings are more character-visible than English strings (1.892 vs. 3.169 characters per token), and character-counting accuracy falls as English words occupy more tokens. Second, reasoning mode is not uniformly helpful: Gemma4-31B is nearly unchanged across modes on the near-saturated tasks, while Qwen3.6-27B is worse with thinking on palindrome detection (0.952 non-thinking vs. 0.886 thinking at four-shot). Third, index_to_span remains largely unsolved; the best four-shot exact-match accuracy is 6.75%. Character-level evaluation needs controlled inputs, paired tests, and analyses of tokenization and reasoning mode rather than aggregate accuracy alone.

Papers announced by arXiv on Sunday, 4 October 2026, covering submissions from 1 October to 2 October 2026.