Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Analytic Number Theory Research
Abstract
A failed primality test can provide new candidates for a Goldbach search: factor the complement and test its distinct prime factors in turn. We study full breadth-first search under this rule, started at the least prime p0(N) >= N/2. A freshly regenerated exhaustive scan of all 4,999,999 even inputs 4 <= N <= 10^7 finds no canonical-root failure. With the successful endpoint included, the mean number of tested vertices is 7.0527, its maximum is 151, and the maximum first-success depth is 10. Changing only the initial prime produces genuine failures: a complete upper-half-root census through 2 * 10^4 has 301 composite-complement failures at six inputs, none from p0. Exact same-input certificates distinguish eventual failure from shallow delay and show that neither p0 nor p1 universally minimizes success depth. Elementary closure arguments identify the unresolved reachability question. The computations do not prove universal canonical success or the binary Goldbach conjectureAI assistance. Generative AI systems were used during the exploratory research process to propose, test, and critique mathematical arguments, assist with computational experiments, and support manuscript preparation. All claims included in this note were checked against the stated computations or proofs before inclusion. The author remains responsible for the content.
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
A comprehensive overview of how enhanced sampling methods are reshaping the field, with a particular focus on the data-driven construction of collective variables, is provided.
Kai Zhu, Enrico Trizio, Jintu Zhang et al.· Chemical Reviews· 58 citations
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
AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduSep 16, 2026