让大模型学会可复用的解题方法，持续改进逻辑推理能力
Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
- 从训练数据和用户交互中提取问题与解法配对，形成外部可存储的方法库
- 通过用户反馈排序方法，新方法可超越旧方法性能
- 提升复杂任务中的事实验证与泛化能力，支持持续学习
大型语言模型在多种语言任务中表现出色，但其推理主要依赖训练数据中的统计模式，难以应对新问题并保持一致逻辑。本文提出一种基于方法的模型，从训练内容、生成回复和用户交互中提取显式的、可复用的解题步骤。每个方法以问题-解法对形式表示，外部存储并根据反馈排名。当收到新查询时，系统检索最相关的方法来引导模型输出。该模型支持持续学习、方法复用与逻辑一致性，超越传统的逐词预测。实验表明，系统显著提升了复杂提示下的事实验证与泛化能力，且通过用户驱动优化的新方法可超越早期方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。