AI Evolves Itself Using Evolutionary Algorithms and LLMs
Researchers demonstrate how AI can recursively improve its coding skills using evolutionary algorithms and large language models.
Researchers have developed a system called Darwin Gödel Machines (DGMs) that enables AI to recursively improve its own coding abilities. This breakthrough leverages evolutionary algorithms and large language models (LLMs) to create self-enhancing AI agents, marking a significant step toward autonomous AI development.
How DGMs Work
DGMs combine two key technologies:
- Evolutionary Algorithms: Inspired by natural selection, these algorithms create variations of AI agents, test their performance, and iteratively refine the best ones.
- Large Language Models (LLMs): LLMs like those powering ChatGPT provide the "intuition" needed to suggest useful code modifications.
The system starts with a base AI agent capable of reading, writing, and executing code. The DGM then:
- Generates multiple variants of the agent.
- Uses LLMs to suggest improvements.
- Tests each variant on coding benchmarks like SWE-bench and Polyglot.
- Retains all variants for "open-ended exploration," allowing even initially poor performers to contribute to future breakthroughs.
The evolution of AI agents, with the best performer marked by a star. (Credit: Jenny Zhang, Shengran Hu, et al.)
Performance Gains
- SWE-bench: Agent performance improved from 20% to 50%.
- Polyglot: Scores rose from 14% to 31%.
Notably, the best-performing agent followed a non-linear path, with temporary dips in performance before achieving breakthroughs. This highlights the value of open-ended exploration.
The lineage of the best agent included temporary setbacks. (Credit: Jenny Zhang, Shengran Hu, et al.)
Implications and Risks
Productivity Boost
- Companies like Microsoft and Google already use AI to generate significant portions of their code (30% and 25%, respectively).
- DGMs could automate the creation of high-performance software beyond human expertise.
Safety Concerns
- Self-improving AI risks becoming uninterpretable or misaligned with human goals.
- Researchers added guardrails, such as sandboxing and code review, to mitigate risks.
The Singularity Debate
- Some experts, like Jürgen Schmidhuber, dismiss fears of a runaway AI "singularity."
- Others, like Zhengyao Jiang, emphasize the need for human creativity to guide AI evolution.
Future Directions
- Combining DGMs with systems like Google DeepMind’s AlphaEvolve, which optimizes algorithms and hardware.
- Extending DGMs to domains like drug design by scoring agents on multiple objectives.
This research represents a major leap toward self-improving AI, with profound implications for both productivity and safety.
Related News
Data-Hs AutoGenesys creates self-evolving AI teams
Data-Hs AutoGenesys project uses Nvidias infrastructure to autonomously generate specialized AI agents for business tasks
AI Risks Demand Attention Over Interest Rate Debates
The societal and economic costs of transitioning to an AI-driven workforce are too significant to overlook
About the Author

Dr. Lisa Kim
AI Ethics Researcher
Leading expert in AI ethics and responsible AI development with 13 years of research experience. Former member of Microsoft AI Ethics Committee, now provides consulting for multiple international AI governance organizations. Regularly contributes AI ethics articles to top-tier journals like Nature and Science.