A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Neura Market
81% of n8n workflow templates that call an external system declare no error handling at all — no retry, no timeout, no error branch. A structural analysis of 5,147 deduplicated automation templates, read from their own executable specifications.
Neura Market
AI went from 0% to 58% of new n8n automation templates in five years, only 1.2% of templates pause for a human, and the top 10% capture over three-quarters of all recorded adoption — from 26,822 workflow specifications across n8n and Make.
Unknown
This paper proposes a framework for interactive AI alignment, distinguishing specification, process, and evaluation alignment to address the dynamic and interactive nature of aligning AI systems with human values.
Unknown
This paper outlines a research agenda for AI safety, identifying five practical problems—accidents, misspecification, and other risks—that arise from poorly specified goals in machine learning systems.
Yihao Chen, Shi Chang, Feng Lin, et al.
SpecFirst introduces a two-stage framework that separates behavioral specification elicitation from code synthesis, significantly improving from-scratch program construction by LLM agents.
Douglas M. Bates, Martin Mächler, Benjamin M. Bolker, et al.
Describes the lme4 package for fitting linear mixed-effects models in R using maximum likelihood or REML, including model specification, optimization, and user extensibility.
Tzafrir Rehan
Test-Driven AI Agent Definition (TDAD) compiles tool-using agents from behavioral specifications, treating prompts as compiled artifacts.