Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
Abstract This reference architecture addresses the structural vulnerability in contemporary AI and social platform systems caused by the implicit coupling of truth evaluation, decision-making, and execution. Released under the Apache-2.0 license, the framework introduces a rigorous separation of concerns through two core semantic entities: ARSHAM SHARIS, a non-probabilistic, deterministic truth and consistency evaluation core operating upstream of action systems, and RON FYRE, a non-referential semantic activation operator governing controlled, irreversible state transitions via append-only authorization gates. Applied to social ecosystem governance (specifically designed for X / Grok integration via the IRIS Impersonation Risk & Integrity System), the architecture combines multi-signal feature extraction (Python/Rust), a low-latency deterministic risk-scoring kernel (C++/Rust), and a policy enforcement engine (FLAG, LIMIT, SUSPEND). This blueprint effectively counters large-scale identity impersonation, automated crypto scams, and coordinated reply networks while preserving platform trust and operational explainability. In alignment with principles of digital integrity and social responsibility, 100 percent of all licensing revenues generated from enterprise deployments of this framework are dedicated to the Beit Ahawah Foundation (בית אהבה) for the reconstruction of Beit Ahawah in Berlin Mitte.
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.
Zheying Zhang, M. Rayhan, Tomas Herda et al.· International Conference on...· 48 citations· ⚡4
This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 44 citations· ⚡2
The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.
Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al.· arXiv.org· 41 citations
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.