Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources

• URL: http://arxiv.org/abs/2606.28370v1
• Date: Mon, 15 Jun 2026 17:02:22 GMT
• Title: Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources
• Abstract summary: Existing AI-enabled interfaces force users to select the right tool.<n>We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem.
• Score: 0.816316992802876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables. We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements slide-adaptive chunking -- recursive chunking for plain-text slides, hierarchical chunking for structured content such as tables, charts, and key-value blocks - achieving $88.3\%$ on our internal enterprise benchmark. Second, a routing layer built on a LoRA fine-tuned Qwen-2.5-1.5B-Instruct model that produces a dual output - modality decision and complexity assessment at $93.8\%$ accuracy and approximately $7\times$ lower cost than frontier-model. Third, a retrieval layer executes complexity-adaptive pipelines: a self-correcting NL2SQL agent at $93.9\%$ G-Eval, and Recursive Language Models reaching $91.0\%$ on multi-hop synthesis queries. Finally, a caching layer validates query equivalence across multiple dimensions beyond embedding similarity, achieving zero false cache hits and $8.4\times$ latency reduction.

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems [56.24850338895714]
  RAG struggles with textbfexploratory reasoning problems (ERPs) that are the complex queries involving high uncertainty and ambiguity.<n>We introduce emphPlanRAG, an RAG framework that modelsERPs of natural language as textbflogical query trees (LQTs).<n>PlanRAG outperforms state-of-the-art iteration-based and graph-based RAG systems on our newly constructed dataset, textbfWikiWeb-ERP.
  arXiv  Detail & Related papers  (2026-07-01T06:43:55Z)
• Rethinking RAG in Long Videos: What to Retrieve and How to Use It? [56.38819694781005]
  We introduce V-RAGBench, a benchmark of $langle$query, evidence chunk, answer$rangle$ triplets that enables faithful, decoupled evaluation of retrieval and generation.<n>We also present CARVE, a method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk.
  arXiv  Detail & Related papers  (2026-06-11T10:05:49Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes [5.276278723196607]
  Agentic DAG-Orchestrated Transformer (A.DOT) Planner is a framework for multi-modal, multi-hop question answering.<n>A.DOT compiles user NL queries into directed acyclic graph (DAG) execution plans spanning both structured and unstructured stores.<n>System decomposes queries into parallelizable sub-queries, incorporates schema-aware reasoning, and applies both structural and semantic validation.
  arXiv  Detail & Related papers  (2026-03-15T05:34:16Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• Cortex AISQL: A Production SQL Engine for Unstructured Data [11.480345698642006]
  AI is deployed in production at Snowflake, where it powers diverse customer workloads across analytics, search, and content understanding.<n>We show how AI-aware query optimization treats AI inference cost as a first-class optimization objective.<n>Second, adaptive model cascades reduce inference costs by routing most rows through a fast proxy model.<n>Third, semantic join query rewriting lowers the quadratic time complexity of join operations to linear.
  arXiv  Detail & Related papers  (2025-11-10T22:14:13Z)
• BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation [3.2476501707160543]
  Existing Large Language Models (LLM) struggle withsql generation from natural instructions due to large schema sizes and complex reasoning.<n>In this work, we explore three multi-agent LLM pipelines, with systematic performance benchmarking across a range of small to large open-source models.<n>Experiments on the Bird-Bench Mini-Dev set reveal that Multi-Agent discussion can improve small model performance, with up to 10.6% increase in Execution Accuracy for Qwen2.5-7b-Instruct seen after three rounds of discussion.
  arXiv  Detail & Related papers  (2025-11-06T08:00:15Z)
• From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL [0.4499833362998488]
  Single-agent approaches often struggle with the semantic and syntactic complexities of spatial queries.<n>We propose a multi-agent framework designed to accurately translate natural language questions into spatial queries.<n>We evaluate our system using both the non-spatial KaggleDBQA benchmark and a new, comprehensive SpatialQA benchmark.
  arXiv  Detail & Related papers  (2025-10-23T22:58:17Z)
• Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs [51.33342412699939]
  Knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. Recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. We propose an effective Query Instruction Parsing (QIPP) that captures latent query patterns from code-like query instructions.
  arXiv  Detail & Related papers  (2024-10-27T03:18:52Z)
• CHESS: Contextual Harnessing for Efficient SQL Synthesis [1.9506402593665235]
  We introduce CHESS, a framework for efficient and scalable text-to- queries. It comprises four specialized agents, each targeting one of the aforementioned challenges. Our framework offers features that adapt to various deployment constraints.
  arXiv  Detail & Related papers  (2024-05-27T01:54:16Z)
• JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning [58.71541261221863]
  Join order selection (JOS) is the problem of ordering join operations to minimize total query execution cost. We present JoinGym, a query optimization environment for bushy reinforcement learning (RL) Under the hood, JoinGym simulates a query plan's cost by looking up intermediate result cardinalities from a pre-computed dataset.
  arXiv  Detail & Related papers  (2023-07-21T17:00:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.