Evolution through large models

OpenAI Blog Papers
genetic-programming large-language-models code-generation evolutionary-algorithms reinforcement-learning

Summary

This paper demonstrates that large language models trained on code can significantly enhance genetic programming mutation operators, enabling the generation of hundreds of thousands of functional Python programs for robot design in the Sodarace domain without prior training data. The approach, called Evolution through Large Models (ELM), combines LLMs with MAP-Elites to bootstrap new conditional models for context-specific artifact generation.

No content available
Original Article
View Cached Full Text

Cached at: 04/20/26, 02:44 PM

# Evolution through large models Source: [https://openai.com/index/evolution-through-large-models/](https://openai.com/index/evolution-through-large-models/) OpenAI## Abstract This paper pursues the insight that large language models \(LLMs\) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic programming \(GP\)\. Because such LLMs benefit from training data that includes sequential changes and modifications, they can approximate likely changes that humans would make\. To highlight the breadth of implications of such evolution through large models \(ELM\), in the main experiment ELM combined with MAP\-Elites generates hundreds of thousands of functional examples of Python programs that output working ambulating robots in the Sodarace domain, which the original LLM had never seen in pre\-training\. These examples then help to bootstrap training a new conditional language model that can output the right walker for a particular terrain\. The ability to bootstrap new models that can output appropriate artifacts for a given context in a domain where zero training data was previously available carries implications for open\-endedness, deep learning, and reinforcement learning\. These implications are explored here in depth in the hope of inspiring new directions of research now opened up by ELM\.

Similar Articles

Towards Diverse Scientific Hypothesis Search with Large Language Models

Hugging Face Daily Papers

This paper proposes an evolutionary framework inspired by parallel tempering that uses multi-temperature sampling and information exchange to improve the diversity and quality of scientific hypotheses generated by large language models, demonstrated across molecular, equation, and algorithm discovery.

Efficient Guided Generation for Large Language Models

Papers with Code Trending

This paper presents an efficient method for guiding LLM text generation with regular expressions and context-free grammars with minimal overhead, implemented in the open-source Python library Outlines.

Discovering Reinforcement Learning Interfaces with Large Language Models

Hugging Face Daily Papers

This paper introduces LIMEN, an LLM-guided evolutionary framework that automatically discovers reinforcement learning interfaces by jointly optimizing observation mappings and reward functions from raw simulator states. The approach reduces manual engineering effort and demonstrates that co-designing observations and rewards outperforms optimizing either component alone.