AutoGenAI: Adaptive Optimization of Prompts, Models and Generation Strategies

Provides provider-agnostic tools for jointly comparing and optimizing prompts, language-model providers, and generation strategies for generative artificial intelligence workflows. Candidate configurations can be evaluated using user-supplied scoring functions, cost and latency measurements, robustness perturbations, Pareto-front screening, budget and latency constraints, prompt evolution, adaptive routing, self-consistency, and text-output ensembles. The core workflow is designed to run offline with deterministic mock providers, while external model application programming interfaces can be connected through user-defined provider functions. Evolutionary search concepts are described by Goldberg (1989, ISBN:0201157675), and multi-objective optimization concepts are related to Deb, Pratap, Agarwal and Meyarivan (2002) <doi:10.1109/4235.996017>.

Version: 0.1.0
Depends: R (≥ 4.1.0)
Imports: jsonlite
Suggests: knitr, rmarkdown, testthat (≥ 3.0.0)
Published: 2026-09-12
DOI: 10.32614/CRAN.package.AutoGenAI (may not be active yet)
Author: Leila Marvian Mashhad [aut, cre]
Maintainer: Leila Marvian Mashhad <leila.marveian at gmail.com>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: AutoGenAI results

Documentation:

Reference manual: AutoGenAI.html , AutoGenAI.pdf
Vignettes: Getting Started with AutoGenAI (source, R code)

Downloads:

Package source: AutoGenAI_0.1.0.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): not available, r-oldrel (arm64): AutoGenAI_0.1.0.tgz, r-release (x86_64): AutoGenAI_0.1.0.tgz, r-oldrel (x86_64): AutoGenAI_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=AutoGenAI to link to this page.