# EA4LLM: A Gradient-Free Approach to Large Language Model Optimization via Evolutionary Algorithms

arXiv: https://arxiv.org/abs/2510.10603 · HTML: https://mlsanity.com/paper/2510.10603/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 12 Oct 2025.

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

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [BBTv2: Towards a Gradient-Free Future with Large Language Models](https://mlsanity.com/paper/2205.11200/) (2022)
- [Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning](https://mlsanity.com/paper/2509.24372/) (2025)
- [Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models](https://mlsanity.com/paper/2403.01754/) (2024)
- [Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning](https://mlsanity.com/paper/2502.06301/) (2025)

## Built on by (most cited first, 5 of 5)

- [Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements](https://mlsanity.com/paper/2608.17310/) (2026)
- [Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation](https://mlsanity.com/paper/2604.21950/) (2026)
- [Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training](https://mlsanity.com/paper/2608.02391/) (2026)
- [Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging](https://mlsanity.com/paper/2608.05541/) (2026)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)

## Abstract (arXiv)

In recent years, large language models (LLMs) have made remarkable progress, with model optimization primarily relying on gradient-based optimizers such as Adam. However, these gradient-based methods impose stringent hardware requirements, demanding high-concurrency, high-memory GPUs. Moreover, they require all neural network operations to be differentiable, thereby excluding many promising non-differentiable architectures from practical use. To address these limitations, we propose EA4LLM, an evolutionary algorithm for optimizing LLMs, and, for the first time, empirically verify full-parameter optimization from the pretraining stage across model sizes ranging from 0.5B to 32B. We conduct extensive experiments and provide key insights into how evolutionary algorithms can effectively optimize neural networks. Our work challenges the prevailing assumption that gradient-based optimization is the only viable approach for training neural networks. It also holds significant potential to reduce the computational cost of training large language models, thereby enabling groups with limited computational resources to participate in deep learning research.