Sep 2026· Zenodo (CERN European Organization for Nuclear Research)· 4 references
Abstract
What this is. Toledo is the programme's single permanent home for equations and their machine checks: a public git repository (https://github.com/morrocwi/toledo) whose tagged releases are deposited under this concept DOI, an MCP server and CLI for lookup, a static read API and a public website (https://morrocwi.github.io/toledo/) that explains every status in plain language and gives AI agents the lookup-before-use rule, the install and the API contract. Founder rules: every equation is looked up here first and registered here before it is written or cited elsewhere; no AI agent in the programme may use an unregistered equation. Release v1.5.0 (counts computed from the files in the tag). 990 canonical entries (current 899, unverified 52, split 30, not_an_equation 9); 592 root rows. Debt pass, stated honestly: the 52 unverified entries were re-opened at their sources and stay unverified because the sources themselves classify them as proposed, partial or open; 111 tier values now carry a source quote and 245 remain untagged because their sources give no tag; all 210 wrapped_related entries were examined and none is derivable from the general theorem it aliases without inventing a correspondence, so each keeps that status with a recorded reason; Coq files now exist for every entry that has formal content — 119 Theta and Causal-Memory Closure readings wrapped (116 closed, 3 with named axioms) and 78 finite-model files for the Effort, Economics of Expertise, Core Epistemic Structure and Recursive Epistemic Tunnel entries — 928 Coq files built one at a time, 277 entries closed; the Causal-Memory Closure root still has no source sentence connecting it to a Genesis root, and a candidate proposition is drafted for the founder rather than asserted. New in this release: 23 readings registered from The Recursive Epistemic Tunnel v2.1 (10.5281/zenodo.22639311) with 23 occurrences on reused objects; a provenance note that the readout_genesis import anchor is a local revision whose additions are not yet on the public remote (public verification holds up to the published head); the catalogue rebuilt with typeset entry names and no overfull lines (A4, 291 pages); the MCP package 1.5.0 ships a prebuilt index. Status and limits. K0 working release. Th_coqc / closed certifies the internal consistency of stated finite models, never empirical truth; every status on the website and in the API is a readout of the registry files at the tagged commit. An AI assistant assisted under the author's direction; no AI system is an author or contributor.
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
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
The “HardFlow” algorithm could help generative AI models produce high-quality outputs that obey strict requirements when “pretty close” doesn’t cut it.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.