Chapter 2 · 2025
Advancing multi-step mathematical reasoning in large language models through multi-layered self-reflection with auto-prompting
Jianing Yang, Yuan Li, Yue Zhang
Abstract
Large Language Models (LLMs) have shown impressive capabilities in various natural language processing tasks, but complex multi-step mathematical reasoning remains a significant challenge. This paper introduces a novel approach to enhance LLM performance in such tasks by integrating multi-layered self-reflection with auto-prompting. Our method enables LLMs to critically evaluate their intermediate reasoning steps and refine their thought processes, leading to more accurate and robust solutions.
Topics
LLM mathematical reasoningmulti-layered self-reflectionauto-promptingchain-of-thoughtcomplex problem-solving
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2025
Venue
Type
ChapterCh. 2
Authors3
Zone III Analysis
Related Papers
Generative Agents: Interactive Simulacra of Human Behav…
2023 · Ch.2
MemGPT: Towards LLMs as Operating Systems
2023 · Ch.2
Cognitive Architectures for Language Agents
2023 · Ch.2
Voyager: An Open-Ended Embodied Agent with Large Langua…
2023 · Ch.2
View all Chapter 2 papers →