A design-oriented framework, an evaluation protocol, and a set of open problems for governed structured-data agents are proposed for retrieval semantics, authorization, intent recognition, entity resolution, evaluation, failure modes, and latency.
Abstract
Retrieval-augmented generation (RAG) has become a common architecture for connecting large language models to enterprise knowledge. Most RAG systems retrieve unstructured documents (PDFs, wiki pages, support tickets) and feed them to an LLM for summarization or question answering. A growing class of enterprise agents, however, must query structured data: relational databases, data warehouses, and analytics APIs where the answer is a computed result, not a retrieved passage. Structured-data querying forces decisions that a document-RAG pipeline never has to make. We group them into seven dimensions: retrieval semantics, authorization, intent recognition, entity resolution, evaluation, failure modes, and latency. For each dimension, we characterize the baseline assumption, explain its limitation for structured data, and describe a generic architectural pattern. As supporting evidence, a controlled synthetic study shows that a staged agent built on this framework eliminates the authorization violations of a direct translate-and-execute baseline under controlled conditions. The primary result is a design-oriented framework, an evaluation protocol, and a set of open problems for governed structured-data agents.
This paper argues that genuine enterprise productivity gains require proactive agents: systems that surface relevant, actionable information to workers before they ask, and proposes the Context Graph, a live relational data structure that models enterprise entities, their relationships, and state transitions over time.
Relational Database Management Systems (RDBMS) hold the vast majority of structured enterprise data. However, applying Large Language Models (LLMs) to perform natural language querying and tabular reasoning directly over relational schemas presents major bottlenecks: full schema injection quickly exhausts context windows, complex join relationships lead to hallucinated SQL syntax, and security risks like invalid query execution constrain enterprise adoption. To overcome these limitations, we present Schema-Aware Query Translation and Tabular Reasoning for Enterprise Databases aka Inference-from-RDBMS, an open-source framework designed for schema-aware query translation, dynamic context pruning, and execution-guided tabular inference over complex RDBMS structures. The framework extracts database metadata to construct an interactive Schema Relationship Graph (SRG), prunes unreferenced tables and foreign-key joins using semantic distance metrics, and passes a minimal schema sub-graph to an execution-validated text-to-SQL generator. We evaluate Inference-from-RDBMS across standard enterprise benchmarks (including SPIDER and real-world multi-table schemas). The experimental results demonstrate that our framework achieves an 88.4% execution accuracy, reduces prompt token overhead by 52%, and cuts end-to-end query translation latency by 41% compared to standard schema-injected baseline models. These results position Inference-from-RDBMS as a robust, secure, and cost-efficient solution for natural language database interfaces in large-scale AI applications.
Harshil Lodhiya· International Journal of Res...· 0 citations
Unstructured documents constitute the majority of enterprise and web data. With the rapid development of large language models(LLMs), researchers have started to build data systems that analyze unstructured textual documents like operating on databases. However, because mainstream retrieval methods still relies on fuzzy matching based on vector similarity, accurately obtaining information and performing structured analysis and reasoning remains a major challenge. To address these limitations, AnnoIndex introduces two core fundamental components. The first is Annotation Index. The system uses a module called SchemaLoop to automatically create hierarchical annotation schemas from the raw corpus, and then uses lightweight language model to extract specific values. It turns scattered unstructured text into a materialized, structured index that enables low-cost filtering and querying. The annotation index avoids the black-box matching of vector similarity and amortizes attribute extraction costs from online queries to a one-time build. The second innovation is a Structured Query Engine. It compiles user questions into execution plans based on SQL extension. It first uses the Annotation Index for precise documents filtering, then gradually applies extraction operations in ascending order of cost, resorting to LLMs only for the remaining minimal fraction of the corpus that require deep semantic understanding. The extracted attributions are merged into the annotation index, reducing the cost of future queries. Experiments on three real-world datasets demonstrate that AnnoIndex consistently outperforms state-of-the-art baselines, achieving the highest average F1 score (0.87) while maintaining robust performance on complex multi-hop join and progressive reasoning queries.
Answering natural language questions over structured databases requires identifying the relevant tables and determining how to join them---a task that demands both schema knowledge and semantic understanding of the user's intent. We present guided table retrieval, a four-phase pipeline that combines deterministic grounding via hash-based predictors, structural exploration of join-graph reachability, LLM-powered disambiguation of sources and targets, and algorithmic merging into minimal, topologically ordered join trees. By decomposing the problem into phases with distinct responsibilities--- determinism, coverage, semantic reasoning, and coherence--- the pipeline avoids the brittleness of end-to-end LLM approaches while leveraging LLMs where their contextual judgment is most needed. We evaluate on BIRD-DEV and the enterprise-scale BEAVER benchmark, achieving 94% and 70% precision respectively, with 92% and 53% F1---substantially outperforming existing baselines on precision and F1 while producing exact join trees that can be directly consumed by downstream query compilers.
Alekh Jindal, J. Pandey, C. Pavlopoulou et al.· 0 citations
Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationships. Existing retrieval-augmented generation (RAG) methods typically index documents as raw chunks and retrieve them through embedding similarity. Their performance degrades when chunk boundaries separate entities from supporting evidence or when a question requires multi-hop reasoning across the corpus. We propose EnSI-RAG (Entity-Structure-Indexed Retrieval-Augmented Generation), a framework that constructs a query-independent, entity-centered index. Each record (e, t, k, v) represents an entity e, its type t, a semantic category k in {property, relation, aspect}, and a value v, while retaining links to the original source passages. At query time, these records serve as retrieval handles, and an LLM synthesizes the retrieved passages into the final answer. This design separates evidence localization from answer synthesis while preserving traceable source evidence. Across Loong and Oolong, EnSI-RAG achieves an average accuracy of 78.24. Relative to the published baseline scores used as references, this is 6.62 points higher, suggesting its effectiveness across these settings. The code is available at https://github.com/RamonMeng/EnSI-RAG.
Xuanyu Meng, Jiashuo Sun, Jash Parekh et al.· 0 citations
Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like telecommunications. However, existing RAG approaches largely overlook the holistic integration of diverse retrieval strengths, leading to inaccurate domain routing, poor utilization of hierarchical document structures, and consequently limited reasoning capabilities over enterprise knowledge. To address these limitations, we present VDGR-RAG, which integrates vector retrieval, directory-driven reasoning, graph traversal, and iterative reflection in a unified framework for accurate enterprise knowledge QA. Specifically, VDGR-RAG is an agentic GraphRAG system that first constructs a Hierarchical Heterogeneous Knowledge Graph ($\text{H}^2$KG) from document chunks to preserve both hierarchical directory structures and semantic relationships, and then employs a set of atomic tools for knowledge retrieval that can be freely composed to navigate the $\text{H}^2$KG: (1) a directory-enhanced routing tool that uses table-of-contents (TOC) structures to route user queries to appropriate domain-specific $\text{H}^2$KGs; (2) a multi-route retrieval tool that combines vector search, TOC-based agentic search, and graph search for comprehensive knowledge retrieval; (3) a directory backtracking tool that corrects knowledge localization biases; and (4) a dynamic reflection tool that iteratively plans the next retrieval phase. We conduct extensive experiments on our enterprise product documents across four wireless domains (e.g., energy saving and fault management). Experimental results demonstrate that our method significantly outperforms a variety of RAG baselines in terms of both knowledge retrieval recall and QA accuracy.
Wenqi Chen, Haofei Yang, Rui Yang et al.· 0 citations