# Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement

arXiv: https://arxiv.org/abs/2508.04289 · HTML: https://mlsanity.com/paper/2508.04289/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely](https://mlsanity.com/paper/2409.14924/) (2024)
- [Empowering LLMs with Logical Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2502.15652/) (2025)
- [Efficient LLM Inference on CPUs](https://mlsanity.com/paper/2311.00502/) (2023)
- [Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm](https://mlsanity.com/paper/2405.06652/) (2024)
- [MedSyn: LLM-based Synthetic Medical Text Generation Framework](https://mlsanity.com/paper/2408.02056/) (2024)
- [Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines](https://mlsanity.com/paper/2411.10681/) (2024)

## Built on by (most cited first, 6 of 6)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning](https://mlsanity.com/paper/2510.10592/) (2025)
- [Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery](https://mlsanity.com/paper/2512.12608/) (2025)
- [Cross-Question Method Reuse in Large Language Models: From Word-Level Prediction to Rational Logical-Layer Reasoning](https://mlsanity.com/paper/2509.05660/) (2025)
- [Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence](https://mlsanity.com/paper/2511.00758/) (2025)
- [Method Decoration (DeMe): A Framework for LLM-Driven Adaptive Method Generation in Dynamic IoT Environments](https://mlsanity.com/paper/2512.21817/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have shown impressive capabilities across a wide range of language tasks. However, their reasoning process is primarily guided by statistical patterns in training data, which limits their ability to handle novel problems and perform consistent logical reasoning. In this paper, we propose a method-based model that enhances LLMs with explicit, reusable procedures extracted from training content, generated responses, and user interactions. Each method is represented as a pair consisting of a problem and its corresponding solution, stored externally and ranked based on feedback. When a new query is received, the system retrieves and applies the most relevant methods to guide the LLM's response. Our model enables continual learning, method reuse, and logical consistency beyond next-token prediction. Experimental results demonstrate that the system improves factual verification and generalization in complex prompts, and that newly learned methods can outperform earlier ones through user-driven refinement.