rule engineering

This study addresses the underexplored nature of rules in AI-powered integrated development environments (IDEs) as an emerging class of software artifacts, whose taxonomy, evolution patterns, and practical impact remain poorly understood. Through a mixed-methods approach analyzing 7,310 rules from 83 open-source projects alongside survey data from 99 developers, this work proposes the first systematic classification framework comprising five top-level categories and 25 subcategories. It reveals a significant discrepancy between developer intent and actual rule configurations, demonstrates that rule evolution is frequent and primarily driven by contextual expansion, and quantifies a substantial improvement in software compliance—increasing from an average of 49.14% to 72.13% (+22.99%)—following rule updates.

Existing approaches inadequately model implicit business rule flows in commercial documents, particularly failing to capture logical dependencies (sequential, conditional, parallel) among rules. Method: We propose ExIde—a framework integrating prompt engineering, chain-of-thought reasoning, and dependency-aware fine-tuning—tailored for 12 state-of-the-art LLMs. Contribution/Results: ExIde introduces the first systematic modeling of inter-rule logical dependencies and establishes BPRF, the first Chinese business rule flow annotation dataset (50 documents, 326 rules). It designs a joint rule-pair representation and dependency labeling paradigm and builds the first LLM evaluation benchmark specifically for rule flow understanding. Experiments on BPRF show ExIde improves rule extraction F1 by 18.7% and achieves up to 89.3% accuracy in dependency classification, significantly demonstrating the effectiveness and interpretability of LLMs in modeling business rule flows.

Manually authoring security detection rules is time-consuming and heavily reliant on domain expertise. Method: This paper proposes RulePilot, an LLM-based intelligent agent that automatically generates high-precision detection rules from natural language specifications. Its core innovation is the introduction of an intermediate representation (IR) as a semantic bridge, decoupling natural language understanding from structured rule generation to jointly ensure syntactic consistency and semantic fidelity. RulePilot operates without human intervention for both rule creation and cross-platform rule translation. Contribution/Results: Experiments show RulePilot achieves a 107.4% improvement in textual similarity over baseline methods, delivers higher detection accuracy in real-world environments, and demonstrates practical efficacy in Singaporean industry deployments—particularly in augmenting junior security analysts’ productivity and reducing dependence on expert knowledge.

Existing legal domain classifiers rely solely on case facts, neglecting ratio decidendi and rule-based constraints, thereby limiting interpretability and logical reasoning capability. To address this, we propose a rule-augmented classifier that— for the first time—systematically integrates formalized precedent rules, court hierarchy, and temporal factors into the classification framework, constructing a multidimensional representation encompassing facts, legal rules, and institutional hierarchy. Methodologically, our approach extends Canavotto et al.’s (2023) formalized rationale model using symbolic logic and hierarchical factor modeling. Experimental results demonstrate that the model not only achieves high accuracy in predicting judicial outcomes for novel cases but also substantially enhances computational traceability, decision auditability, and legally grounded interpretability. By unifying formal rigor with judicial pragmatism, our framework establishes a novel paradigm for legal AI systems.

Legacy systems written in COBOL, PL/I, or Assembly—common in banking and telecommunications—are often undocumented and lack original developers, hindering comprehension and modernization. Method: This paper proposes a multi-language, cross-platform, customizable framework for constructing software knowledge graphs and interactively defining architectural boundaries. It integrates static code analysis, data schema parsing, and custom ontology modeling to enable expert-guided, incremental analysis of source code and data architecture, automatically identifying business- and data-driven logical boundaries and visualizing cross-boundary dependencies. Contribution/Results: The framework introduces the first knowledge-graph-driven approach for progressive modernization path planning and impact analysis. Evaluated on two real-world industrial systems, it significantly improves system understanding efficiency and enhances the accuracy of modernization strategy design.

This study addresses the lack of a systematic synthesis and cross-directional integration of formal grammars in business process management (BPM). Through a systematic literature review of 34 core studies, it identifies and integrates seven distinct application areas of formal grammars in BPM for the first time, revealing their largely isolated development. Leveraging theoretical foundations such as the Bunge-Wand-Weber ontology, process algebras, graph grammars, attribute grammars, and grammar inference, the work constructs a comprehensive taxonomy that clarifies the role of formal grammars across the entire BPM lifecycle—including process design, modeling, execution, verification, and mining. Furthermore, it articulates five corpus-based open challenges, laying the groundwork for a unified syntactic theory and its deeper integration into BPM research and practice.

This study addresses the absence of a general principled framework for schema engineering workflows and the difficulty existing systems face in composably representing schema operations. To overcome these limitations, this work proposes a typed logic-based workflow framework. By defining typed representations of fixed components, the approach translates schema operations into composable query chains, thereby decoupling workflow definitions from execution constraints. Furthermore, it designs an LLM agent-driven execution pipeline to enable automated analysis. Experiments conducted on the WIPO dataset successfully execute three categories of query tasks, including exemplar mining. The results validate performance variations across different LLM configurations alongside their error localization capabilities. Ultimately, this research establishes a modular and orchestrable paradigm for schema engineering.

研究通过SuriCap平台和CTF式工作坊，分析了60名参与者创建网络入侵检测规则的过程与方法，揭示经验对规则质量影响有限，并指出标记数据的重要性。

研究通过语言模型解释问题，确定性策略选择并运行预批准分析程序的方法解决企业分析问题，使用关系操作等确保结果可重现。

This work addresses the challenge of maintaining consistency between natural language business rules and their programmatic implementations in large-scale systems by proposing the SIRNA framework. SIRNA is the first approach to integrate large language models with SMT solvers, automatically translating natural language rules into formal SMT specifications and verifying their consistency against SMT representations derived from code. By synergistically combining natural language understanding with formal verification, the method substantially reduces both false positive and false negative rates. Evaluated on a tax cost calculation case study, SIRNA demonstrates high precision and interpretability, offering a novel paradigm for ensuring the fidelity of business rule enforcement in complex software systems.