implement rule-based systems

This work addresses the inefficiency and high cost of compliance testing in highly regulated domains, where current practices rely on manual translation of regulations into test cases by experts. While large language models (LLMs) offer automation potential, they often suffer from hallucination, and existing hybrid approaches still require significant human modeling effort. To overcome these limitations, the authors propose RAFT, a novel framework that explicitly extracts implicit regulatory knowledge from multiple LLMs and leverages an adaptive purification-aggregation strategy with dynamic prompt injection to automatically generate domain-specific meta-models, formalized requirements, and testability constraints—enabling fully automated, human-intervention-free compliance test generation. Experiments in financial, automotive, and power sectors demonstrate that RAFT achieves expert-level performance, significantly outperforming state-of-the-art methods while drastically reducing test case generation and review time.

This work addresses critical challenges in safety-critical rule-based systems—namely poor scalability, fragility, and goal mis-specification—which often lead to reward hacking and failures in formal verification. To overcome these limitations, the authors propose a neuro-symbolic causal framework that integrates first-order logic abductive trees, structural causal models, and deep reinforcement learning within a MAPE-K control loop. A novel meta-layer architecture enables the automatic synthesis and formal verification of rules from natural language objectives. This meta-layer comprises a goal/rule synthesizer and a rule verification engine, which iteratively generate necessary and sufficient causal rule sets grounded in legal and safety principles provided by human experts. Evaluated in an autonomous driving scenario, the approach successfully derives a minimal yet complete rule set, formally encoded as logical constraints, demonstrating its modularity, traceability, and practical applicability.

This work addresses the challenge of providing verifiable safety assurance for robotic systems in safety-critical domains, where traditional assurance cases rely on manually generated evidence that is costly, error-prone, and difficult to maintain. The paper proposes a model-based automated approach that deeply integrates formal verification into the assurance workflow. It employs RoboChart—a domain-specific modeling language with formal semantics—to capture system designs, and introduces a template-driven mechanism to automatically translate natural-language requirements into formal assertions. These assertions are then discharged through a combination of model checking and theorem proving tools, yielding formally verified evidence that can be seamlessly integrated into assurance cases. Case studies demonstrate that the proposed method significantly enhances the reliability, maintainability, and degree of automation in safety argumentation.

To address the time-consuming and error-prone nature of manually constructing logical specifications for complex systems, this paper proposes an automated approach for inferring formal logical specifications from process event logs. Methodologically, it integrates workflow mining, pattern-driven logical translation, SMT solving (via Z3), and automated theorem proving (via Vampire) to achieve end-to-end generation of verifiable logical specifications from process models. Key contributions include: (i) the first unified empirical evaluation of specification quality on diverse, real-world event logs; (ii) a systematic analysis of how noise impacts specification structure and testability; and (iii) formal guarantees of satisfiability, internal consistency, and requirement conformance for generated specifications. Experimental results demonstrate high verification success rates and engineering practicality—even on noisy, real-world logs.

To address the inefficiency and error-proneness of manual regulatory compliance checking, this paper proposes an OWL DL formalization method for natural language specifications. The method introduces a novel structured text annotation scheme and employs a rule-driven deterministic transformation algorithm to automatically map specification texts to OWL DL ontologies. It further integrates Protégé with the HermiT reasoner to enable machine-readable semantic representation and automated compliance verification. A proof-of-concept evaluation in the construction domain demonstrates successful translation of multiple natural language regulations into OWL DL ontologies and accurate identification of compliant and non-compliant scenarios. This work bridges a critical gap between regulatory semantic modeling and automated reasoning, delivering a scalable, methodology-driven foundation for automating compliance checking.

Current AI systems rely heavily on manual auditing and documentation, which hinders scalable governance for automated services. This work proposes Ontological Knowledge Blocks (OKBs), a novel framework that formalizes regulatory obligations as quintuples comprising ontologies, SHACL rules, evidence requirements, and provenance links. By leveraging RDF/OWL modeling, PROV-O for provenance tracking, and an intermediate representation–driven deterministic compiler, the approach enables dynamic switching of governance configurations without modifying service code. Evaluation in an AI-assisted HPC scheduling scenario demonstrates that compliance checks are configuration-sensitive, violations accumulate strictly additively, SHACL validation incurs only 12.6–100.3 milliseconds of latency, and the Combined configuration provides the most comprehensive coverage.

研究通过将法规转化为可执行代码和决策树，利用大语言模型进行结构化、基于证据的合规性评估，提高输出的法律逻辑性和准确性。

Manually authoring causal logic specifications—such as interlock conditions and cause-effect matrices—is inefficient and prone to inconsistencies, failing to meet the demands of modern process safety. This work proposes the first semantic-AI framework that integrates a modular, ontology-aligned knowledge graph with a constrained large language model to enable end-to-end automatic generation of verifiable safety specifications from a unified semantic representation. By leveraging ontology-based modeling, prompt constraints, SWRL rule generation, and machine-interpretable semantic representations, the approach successfully produces causally coherent, diagnostically explicit, and machine-verifiable specifications in a modular plant case study. The method substantially reduces manual intervention while significantly enhancing the automation and reliability of safety specification generation.

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.

This work addresses the challenge of control-flow violations that arise when large language model (LLM) agents automate high-judgment quality management processes in regulated industries, often due to insufficient integration of symbolic structures such as regulatory rules and typed process models. To overcome this limitation, the paper introduces a “compliance-by-construction” paradigm, which internalizes compliance constraints as core components of the agent architecture rather than relying solely on external guardrails. By synergistically combining LLMs with symbolic systems—integrating typed process models, formal compliance constraints, and neuro-symbolic reasoning—the approach structurally prevents violations while preserving the ability to detect semantic errors. The study also systematically delineates the foundational and capability-level challenges required to realize this paradigm, offering a viable neuro-symbolic pathway for automation in regulation-intensive domains.