# Recipes for Creativity: Iterative Generation and Evaluation in Large Language Models

arXiv: https://arxiv.org/abs/2608.07243 · HTML: https://mlsanity.com/paper/2608.07243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Do LLM Evaluators Prefer Themselves for a Reason?](https://mlsanity.com/paper/2504.03846/) (2025)
- [Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity](https://mlsanity.com/paper/2303.12003/) (2023)
- [Collective Critics for Creative Story Generation](https://mlsanity.com/paper/2410.02428/) (2024)
- [Creative Beam Search: LLM-as-a-Judge For Improving Response Generation](https://mlsanity.com/paper/2405.00099/) (2024)
- [Do LLMs Agree on the Creativity Evaluation of Alternative Uses?](https://mlsanity.com/paper/2411.15560/) (2024)
- [Efficiency at Scale: Investigating the Performance of Diminutive Language Models in Clinical Tasks](https://mlsanity.com/paper/2402.10597/) (2024)

## Abstract (arXiv)

Generative models are often evaluated through singular artifacts, whereas human creativity typically emerges through iterative generation, appraisal, and refinement. This pilot study examines whether iterative search improves LLM creativity by adapting FunSearch to recipe generation for the 2024 Pillsbury Bake-Off and evaluating outputs against human benchmarks using TTCT-based LLM evaluation. Across two experiments, we test iteration count, generator temperature, and in-loop selection-scorer model size. Results show that iterative generation-selection can produce recipes with creativity scores comparable to human benchmarks, but additional iterations alone do not improve creativity. The in-loop evaluator matters most: a smaller selection scorer yields significantly higher scores across most TTCT dimensions, while temperature has limited effects except for originality. These findings suggest that evaluator design is a first-order design variable in subjective creative search.