query decomposition

This paper addresses the failure of conventional equivalence-based query rewriting when original data tables are inaccessible due to access control policies, privacy constraints, or prohibitive retrieval costs. To overcome this, we propose INQURE, a semantic intent-preserving query rewriting framework. Unlike traditional approaches relying on syntactic equivalence and query plan optimization, INQURE introduces, for the first time, large language model (LLM)-driven intent understanding and cross-table reconstruction—enabling semantically consistent rewriting across structurally heterogeneous and non-aligned schemas. The system incorporates pre-filtering of candidate tables, pruning heuristics, and learned ranking to form an end-to-end rewriting pipeline. Evaluated on a benchmark spanning 900+ real-world database schemas, INQURE demonstrates superior rewriting quality and practical utility. A user study further confirms its effective trade-off between execution feasibility and fidelity of analytical insights.

Existing natural language interfaces to databases lack systematic evaluation frameworks and design theories. This work proposes QUEST, a novel framework that integrates the general-purpose FAR operation schema—Filter, Aggregate, Return—with the W5H semantic dimensions (Who, What, Where, When, Why, How) to enable structured analysis and evaluation of text-to-SQL query semantics. Through semantic annotation and structural parsing, the study validates the universality of the FAR schema across five cross-domain datasets comprising 120,464 queries. The analysis further reveals significant inter-domain disparities in semantic distributions: for instance, medical queries predominantly focus on WHEN and WHO, while WHY and HOW are nearly absent, underscoring a critical challenge for machines in performing deep reasoning over structured data.

This work addresses the inefficiency faced by data analysts who must repeatedly submit and integrate multiple related queries to explore salient data patterns. To streamline this process, the paper introduces the ANALYZE operator, which formalizes such exploratory analysis as five auxiliary cube queries, enabling comprehensive 360-degree examination of specific data subsets. Leveraging multi-query optimization (MQO), the authors devise three query merging and execution strategies—Mid-MQO, Min-MQO, and Max-MQO—that significantly improve execution efficiency while preserving result equivalence. Experimental evaluation demonstrates that Mid-MQO consistently delivers the best overall performance across most scenarios, whereas Max-MQO excels when sibling queries are numerous and exhibit high overlap.

This work investigates the capability of large language models (LLMs) to determine semantic equivalence between SQL queries, focusing on two critical definitions—semantic equivalence and relaxed equivalence—to enhance the reliability of semantic-level evaluation in text-to-SQL and related generation tasks. We propose a dual-path prompting framework: (1) *Miniature&Mull*, which performs lightweight execution-based verification via counterexample construction; and (2) *Explain&Compare*, which generates natural-language explanations of logical discrepancies and conducts structured syntactic-semantic comparison. To our knowledge, this is the first systematic evaluation of LLMs’ effectiveness and limitations in SQL equivalence judgment without requiring large-scale query execution or human annotations. Experimental results demonstrate that our approach significantly outperforms conventional execution accuracy metrics and achieves reasonable discrimination performance on semantic equivalence tasks. It establishes a novel, interpretable, lightweight, and semantics-aware paradigm for evaluating SQL generation quality.

This work addresses the limitations of existing large language model–based search agents, whose retrieval accuracy and reasoning performance are often compromised by the generation of low-quality intermediate queries. To mitigate this issue, the paper proposes a process reward–driven dual-level credit assignment mechanism coupled with a selective query optimization strategy. Furthermore, a three-stage curriculum learning framework—progressing from imitation to generalization—is designed to guide the agent in internalizing the ability to generate high-quality queries. Empirical evaluations demonstrate that the proposed approach significantly outperforms current state-of-the-art methods across multiple benchmarks, achieving notable improvements in both query quality and search efficiency.

Answering complex first-order logical queries involving projection, intersection, union, and negation over incomplete knowledge graphs is highly challenging. This work proposes ROG, a novel framework that integrates query-aware neighborhood retrieval with chain-of-thought reasoning from large language models. ROG recursively decomposes multi-operator queries into single-operator subqueries and leverages compact, relevant neighborhood evidence at each reasoning step. By introducing a retrieval-augmented, stepwise reasoning mechanism along with caching and reuse of intermediate answer sets, ROG significantly enhances reasoning consistency and robustness—particularly for high-complexity and negation-containing queries. Experimental results demonstrate that ROG consistently outperforms strong embedding-based baselines across standard benchmarks.

This work addresses the challenge of compiling natural language queries into backend query languages in document-centric, hybrid, and heterogeneous data environments, where semantic intent is often ambiguous or incomplete. The authors propose the NLIQ framework, which introduces a “goal sufficiency” criterion to classify queries according to their semantic determinacy. It emphasizes that when intermediate goals must be dynamically constructed, intermediate representations should serve as core semantic objects rather than mere syntactic intermediaries. Through conceptual analysis, case modeling, and formal categorization, the study establishes a unified query paradigm that integrates goal recognition, intermediate representation design, and heterogeneous execution. This framework provides a theoretical foundation for natural language querying in complex data settings and opens new research directions in semantic goal construction, heterogeneous compilation, and answer generation.

Current evaluations of large language model reasoning overly rely on final-answer accuracy, making it difficult to diagnose the reasoning process itself. This work proposes a process-oriented evaluation framework centered on adaptive, multi-step search, modeling reasoning as an input-dependent, variable-depth search procedure. The approach emphasizes assessing the faithfulness and effectiveness of intermediate reasoning trajectories rather than just end results. By leveraging intermediate decoding and explicit reasoning traces, the method analyzes model behavior in step selection and termination mechanisms, revealing structural limitations of single-pass forward architectures in achieving variable-depth computation. This shift enables the development of more interpretable and debuggable evaluation standards that capture the dynamics of reasoning beyond static correctness.

This work addresses the lack of rigorous mathematical formalization in decomposition-based reasoning for multi-hop question answering. It introduces operad theory into the analysis of large language model reasoning by constructing a question operad $Q$, where question templates are treated as operations and sub-answers as inputs to be composed. The question-answering model is thereby interpreted as an algebra over this operad, providing a formal framework for problem decomposition and composition. Building on this foundation, the paper proposes operadic consistency—a novel metric for evaluating the coherence of multi-step reasoning. Experiments across 12 large language models and 4 multi-hop question answering benchmarks demonstrate that this metric exhibits strong correlation with answer accuracy and significantly outperforms temperature-based self-consistency baselines.