Aug 2026· TH Wildau Engineering and Natural Sciences Proceedings· 0 citations· 5 references
TL;DR
An LLM-based prototype designed to support the application of a documented rule catalog within GitLab merge requests is presented, which demonstrates the technical feasibility of integrating rule-based governance with LLM-supported contextual interpretation in a practical GitLab workflow.
Abstract
Code reviews are a central component of collaborative software development, yet they often require considerable manual effort in practice. Ensuring consistent compliance with project-specific standards can be challenging, particularly when these standards require contextual interpretation of code, naming conventions, or documentation.
This paper presents an LLM-based prototype designed to support the application of a documented rule catalog within GitLab merge requests. The agent is integrated into the existing workflow and is triggered automatically by merge request events. It analyzes the source code contained in a merge request and evaluates it against explicitly defined project rules.
To ensure structured and consistent output, a predefined JSON schema guides the model’s response and enables validation before publication. Invalid or non-parseable outputs are detected and not posted to the merge request.
The approach is not intended to replace human reviewers, but to support them in the systematic application of documented project standards. The implementation demonstrates the technical feasibility of integrating rule-based governance with LLM-supported contextual interpretation in a practical GitLab workflow.
An agentic document verification framework that moves beyond passive retrieval to active, rule-aware compliance checking and incorporates a Propose-Decide-Evidence governance model is presented, retaining the human engineer as final decision-maker while establishing an efficient, auditable, continuously improving compliance workflow.
Ka Tai Lau, Man Chit, Jovian Cheung et al.· AHFE International· 0 citations
This paper presents a framework integrating Knowledge Graphs and Large Language Models to support a more extensible design review environment, and demonstrates its ability to retrieve and execute existing rules from the KG, capture new requests during design, and maintain a verifiable, adaptive compliance checking system.
Maen Alnuzha, Tanya Bloch· Journal of Information Techn...· 1 citation
CompVault, an Enhanced Retrieval-Augmented Generation (ERAG)-based Artificial Intelligence Compliance Monitoring and Report Generation System for intelligent regulatory compliance assessment, and results indicate that the ERAG-based framework can be used as an efficient, scalable, and explainable solution for regulatory compliance monitoring and automated report generation.
S. N., Sathyapriya P., Vishnu Priya R. M. et al.· Journal of Information Techn...· 0 citations
This work presents StructureClaw, an artifact-centered workbench in which LLM agents operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends, together with StructureClaw-Bench, an executable benchmark of 150 controlled scenarios spanning standard workflows, interactive robustness, and multimodal structural-model reconstruction.
Sizhong Qin, Yi Gu, Yao Jiang et al.· arXiv.org· 0 citations
Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners. Recent advances in Large Language Models (LLMs) offer promising capabilities for interpreting developer intent, but their effectiveness in repository management tasks is limited by the need for formal reasoning. This work introduces Git-Assistant, an AI-based assistant that combines LLMs with automated planning to support developers in executing non-trivial git operations. The assistant analyzes repository context, translates natural language requests into actionable command sequences, and incorporates planning techniques to ensure correctness and safety. We present a systematic evaluation methodology using synthetic and randomized git environments, comparing the performance of LLM-only and planning-augmented variants across multiple metrics. Experimental results demonstrate that integrating formal reasoning with LLMs improves reliability and reduces errors in repository management, highlighting the potential of hybrid AI approaches for intelligent developer assistance.
A. Ruiz, Tom'as de la Rosa, Daniel Borrajo· arXiv.org· 0 citations
Agent systems validate inputs, tool calls, and generated objects. The final package often escapes the same scrutiny. In one DRSS release, the ledger supported 60 points and a failed certificate; the report announced a 100-point Gold Path. Every local gate was green. The package contradicted itself. We study that failure alongside Schema Docs, where similar faults became product contracts, and Brand Shuttle GEO, where evidence is turned into repair work. The result is a candidate Schema-SIP Relational Conformance profile (SIP-RC). It models a release as a graph: claims point to evidence, decisions carry bounded authority, derived artifacts retain their execution conditions and lineage, and published bytes must match the package that was checked. Hard failures cannot be averaged away, and a validator recomputes critical decisions on a separate path. The paper establishes the failure class and shows that several mechanisms are practical. Whether the full profile performs better than existing checks remains an open experiment.
Tengjiao Liu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
