Adaptive Optimization of Prompts, Models and Generation Strategies
Overview
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.
- Initial provider-agnostic optimization framework.
- Added joint prompt-provider-generation benchmarking.
- Added prompt evolution, Pareto optimization, budget and latency constraints, robustness testing, adaptive routing, and ensemble tools.
- Added deterministic offline mock providers, tests, and vignettes.
- Added explicit
stats::runif()namespace import and CRAN-friendly documentation formatting.
From NEWS.md in the release
Install
Health
- OK13 OKNow
- OK6 OK2026-09-13
Documentation
- Help pages
- 11includes a package overview page
- Examples that run
- 100%4 run in a plain check
- Exported functions with examples
- 44%
- Documented parameters
- 58%
- Return-value docs
- 100%
- Help pages citing references
- 0%
Downloads
Dependencies
Installing AutoGenAI adds 1 package (1 with compiled code, 1.0 MB of source tarballs). Heaviest: jsonlite 1.0 MB.
Code & Tests
Datasets
People & History
- 0.1.0Latest2026-09-12 · current release
- RR 4.6.0 released · 2026-04-24
Package metadata
- First published
- 2026-09-12
- Total releases
- 1 / 1 yrs
- License
- MIT + file LICENSE OSI
- Minimum R
- ≥ 4.1.0
- Download size
- 23 KB
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("AutoGenAI")This package has no citation file, so citation() returns this entry built from DESCRIPTION.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-22, which the citation names so these numbers can be found later. More on citing and the projects behind them.