Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914178051080192 |
|---|---|
| author | Loureiro, André de Souza Valverde-Rebaza, Jorge Noguez, Julieta Escarcega, David Marcacini, Ricardo |
| author_facet | Loureiro, André de Souza Valverde-Rebaza, Jorge Noguez, Julieta Escarcega, David Marcacini, Ricardo |
| contents | Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the Multi-Layered Self-Reflection with Auto-Prompting (MAPS) framework, a novel approach designed to enhance multi-step mathematical reasoning in LLMs by integrating techniques such as Chain of Thought (CoT), Self-Reflection, and Auto-Prompting. Unlike traditional static prompting methods, MAPS employs an iterative refinement process. Initially, the model generates a solution using CoT prompting. When errors are detected, an adaptive self-reflection mechanism identifies and analyzes them, generating tailored prompts to guide corrections. These dynamically adjusted prompts enable the model to iteratively refine its reasoning. Experiments on four well-established benchmarks across multiple LLMs show that MAPS significantly outperforms standard CoT and achieves competitive results with reasoning-optimized models. In addition, MAPS enables general-purpose LLMs to reach performance levels comparable to specialized reasoning models. While deeper reflection layers improve accuracy, they also increase token usage and costs. To balance this trade-off, MAPS strategically limits reflection depth, ensuring an optimal balance between cost and reasoning performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23888 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting Loureiro, André de Souza Valverde-Rebaza, Jorge Noguez, Julieta Escarcega, David Marcacini, Ricardo Computation and Language Machine Learning Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the Multi-Layered Self-Reflection with Auto-Prompting (MAPS) framework, a novel approach designed to enhance multi-step mathematical reasoning in LLMs by integrating techniques such as Chain of Thought (CoT), Self-Reflection, and Auto-Prompting. Unlike traditional static prompting methods, MAPS employs an iterative refinement process. Initially, the model generates a solution using CoT prompting. When errors are detected, an adaptive self-reflection mechanism identifies and analyzes them, generating tailored prompts to guide corrections. These dynamically adjusted prompts enable the model to iteratively refine its reasoning. Experiments on four well-established benchmarks across multiple LLMs show that MAPS significantly outperforms standard CoT and achieves competitive results with reasoning-optimized models. In addition, MAPS enables general-purpose LLMs to reach performance levels comparable to specialized reasoning models. While deeper reflection layers improve accuracy, they also increase token usage and costs. To balance this trade-off, MAPS strategically limits reflection depth, ensuring an optimal balance between cost and reasoning performance. |
| title | Advancing Multi-Step Mathematical Reasoning in Large Language Models through Multi-Layered Self-Reflection with Auto-Prompting |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2506.23888 |