Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
This addresses the problem of inconsistent reasoning in LLMs for users needing reliable AI responses, though it appears incremental as it builds on existing LLM frameworks.
The paper tackles the limitation of LLMs in handling novel problems and logical reasoning by proposing a method-based model that extracts, stores, and reuses explicit procedures from training data and interactions, resulting in improved factual verification and generalization in complex prompts.
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.