PulseAugur
EN
LIVE 20:53:38

New AI agents tackle complex enterprise data queries across modalities · 2 sources tracked

By PulseAugur Editorial · [3 sources] ·

Researchers have developed two distinct AI systems designed to improve natural language querying over complex enterprise data. The first, a semantic-layer-mediated agent, translates natural language into SQL by reasoning over an intermediate representation called Semantic Model Query (SMQ), achieving 94.15% execution accuracy on the Spider2-snow benchmark using Gemini 3 Pro. The second system, COGNI, is a conversational BI platform that handles both structured data and unstructured documents by employing a routing layer fine-tuned on Qwen-2.5-1.5B-Instruct, which directs queries to either a self-correcting NL2SQL agent or recursive language models, demonstrating high accuracy and cost efficiency. AI

IMPACT These systems aim to significantly improve how businesses interact with and extract insights from complex, heterogeneous data sources.

RANK_REASON Two distinct research papers detailing novel AI systems for natural language querying over enterprise data.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New AI agents tackle complex enterprise data queries across modalities · 2 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Two distinct research papers detailing novel AI systems for natural language querying over enterprise data.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
88 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [3]

  1. arXiv cs.CL TIER_1 English(EN) · Ha Jeong Kim, Saksonita Khoeurn, Ye Ji Yoon ·

    A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases

    arXiv:2606.31041v1 Announce Type: new Abstract: Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, hetero…

  2. arXiv cs.AI TIER_1 English(EN) · Darshita Rathore, Vineet Kumar, Vaibhav Singal, Ankur Vivek Singh, Anindya Moitra ·

    Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources

    arXiv:2606.28370v1 Announce Type: cross Abstract: Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled in…

  3. arXiv cs.CL TIER_1 English(EN) · Ye Ji Yoon ·

    A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases

    Natural language-to-SQL (NL2SQL) over real-world enterprise databases remains significantly more challenging than on academic benchmarks. Enterprise schemas often contain hundreds of physical tables with cryptic column names, heterogeneous SQL dialects, and complex analytical wor…

RELATED ENTITIES

RELATED TOPICS