arXiv AI August 11, 2026 By Morris Lee

Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline

arXiv:2608. 09254v1 Announce Type: new Abstract: LLM analytics agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questions the warehouse cannot answer, deprecated columns after a schema change, and queries that execute successfully while returning the wrong business number.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 11

Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

arXiv:2608. 07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean.

By Mike Helwig

llms benchmarks data-engineering

arXiv AI

Jul 10

When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals

arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.

By Kaihua Ding

llms safety

arXiv AI

1d ago

Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL

arXiv:2608. 16663v1 Announce Type: cross Abstract: Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query.

By Yi Ai

llms benchmarks data-engineering

arXiv AI

Jul 10

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.

By Benedikt J. Wagner

llms

arXiv AI

Jul 21

Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.

By Arunabh Dastidar (for the Leni Team)

agents benchmarks

arXiv AI

Aug 12

AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning

arXiv:2606. 00671v2 Announce Type: replace Abstract: We present AXIOM, a trust-first neuro-symbolic architecture for natural-language mathematical reasoning.

By Alessio Bruno

llms benchmarks safety

Related stories

Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals

Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Self-Explaining Mathematical Reasoning