Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
D.R.O.N.E. (Dynamic Responsive Optimized Neural Engine) is a small artificial intelligence written from scratchin C. It uses no outside libraries and no pre-trained model, and it runs offline on an ordinary CPU. Each AI builton the engine is called a drone.The design splits the work of answering into two parts. An exact core, written as ordinary C, reads everymessage, keeps track of the conversation and decides what should happen: run an action, state a thought, orjust talk. A neural brain then puts that decision into words. Its neurons are small pieces of x86-64 machinecode that the engine writes at run time. Between the two parts, a set of engine checks keeps the reply honest:it must match what was really done and computed.This paper explains how each part works and how to use it. Every mechanism is shown with a real exampletaken from the running system, and the mathematics is given where it is used. Section 4 follows one messagethrough the whole engine, step by step, and section 13 shows how to build, run, extend and train it. The projecthas only just started, so the numbers are a snapshot from October 3, 2026, after eight days and six trainingrounds, not a finished result.
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
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.