# Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models

arXiv: https://arxiv.org/abs/2402.05376 · HTML: https://mlsanity.com/paper/2402.05376/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 2 of its 36 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 2 of 2)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [IDPG: An Instance-Dependent Prompt Generation Method](https://mlsanity.com/paper/2204.04497/) (2022)

## Built on by (most cited first, 15 of 15)

- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [Instance-adaptive Zero-shot Chain-of-Thought Prompting](https://mlsanity.com/paper/2409.20441/) (2024)
- [Nature-Inspired Population-Based Evolution of Large Language Models](https://mlsanity.com/paper/2503.01155/) (2025)
- [SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models](https://mlsanity.com/paper/2506.12935/) (2025)
- [Deep Insights into Automated Optimization with Large Language Models and Evolutionary Algorithms](https://mlsanity.com/paper/2410.20848/) (2024)
- [Zero-Shot Verification-guided Chain of Thoughts](https://mlsanity.com/paper/2501.13122/) (2025)
- [Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology](https://mlsanity.com/paper/2411.03495/) (2024)
- [Embedding Domain-Specific Knowledge from LLMs into the Feature Engineering Pipeline](https://mlsanity.com/paper/2503.21155/) (2025)
- [A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge](https://mlsanity.com/paper/2601.13383/) (2026)
- [Document-Level Event Extraction with Definition-Driven ICL](https://mlsanity.com/paper/2408.05566/) (2024)
- [Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity](https://mlsanity.com/paper/2509.22054/) (2025)
- [Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning](https://mlsanity.com/paper/2512.20647/) (2025)
- [Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models](https://mlsanity.com/paper/2503.23503/) (2025)
- [Exchange of Perspective Prompting Enhances Reasoning in Large Language Models](https://mlsanity.com/paper/2506.03573/) (2025)
- [Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution](https://mlsanity.com/paper/2603.01784/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks and exhibited impressive reasoning abilities by applying zero-shot Chain-of-Thought (CoT) prompting. However, due to the evolving nature of sentence prefixes during the pre-training phase, existing zero-shot CoT prompting methods that employ identical CoT prompting across all task instances may not be optimal. In this paper, we introduce a novel zero-shot prompting method that leverages evolutionary algorithms to generate diverse promptings for LLMs dynamically. Our approach involves initializing two CoT promptings, performing evolutionary operations based on LLMs to create a varied set, and utilizing the LLMs to select a suitable CoT prompting for a given problem. Additionally, a rewriting operation, guided by the selected CoT prompting, enhances the understanding of the LLMs about the problem. Extensive experiments conducted across ten reasoning datasets demonstrate the superior performance of our proposed method compared to current zero-shot CoT prompting methods on GPT-3.5-turbo and GPT-4. Moreover, in-depth analytical experiments underscore the adaptability and effectiveness of our method in various reasoning tasks.