让大模型像人一样从错误中学习，无需更新参数就能持续进化推理能力。
Composite Learning Units: Generalized Learning Beyond Parameter Updates to Transform LLMs into Adaptive Reasoners
- 构建动态知识库，分通用与任务专用空间存储经验。
- 在密码推理任务中自主发现隐藏规则，准确率显著优于传统模型。
- 适合需要持续学习和自适应推理的智能系统开发人员。
人类学习依赖于从错误中吸取教训、通过反馈调整并不断深化理解——这一过程在静态机器学习模型中常被忽略。本文提出复合学习单元（CLUs），旨在将大语言模型等推理系统转化为具备泛化连续学习能力的学习者，无需传统参数更新即可通过持续交互与反馈提升推理能力。CLUs基于新架构，维护一个动态知识库：包含广泛可复用洞察的通用知识空间，以及针对特定任务的提示专用知识空间。通过目标驱动的交互，CLUs迭代优化这两个知识空间，使系统能动态适应复杂任务，提取细微洞察，并自主积累过往经验。我们在密码学推理任务中验证其有效性：模型通过反馈不断演化对隐藏变换规则的理解。传统模型难以把握深层逻辑，而CLUs则凭借迭代式、目标导向的过程表现出色。专门组件——知识检索、提示生成与反馈分析——在强化反馈回路中协同工作，使系统既能保留失败与成功记忆，又能自主适应，有效应用复杂推理，持续从错误中学习并继承突破性进展。
原文摘要 · Abstract (English)
Human learning thrives on the ability to learn from mistakes, adapt through feedback, and refine understanding-processes often missing in static machine learning models. In this work, we introduce Composite Learning Units (CLUs) designed to transform reasoners, such as Large Language Models (LLMs), into learners capable of generalized, continuous learning without conventional parameter updates while enhancing their reasoning abilities through continual interaction and feedback. CLUs are built on an architecture that allows a reasoning model to maintain and evolve a dynamic knowledge repository: a General Knowledge Space for broad, reusable insights and a Prompt-Specific Knowledge Space for task-specific learning. Through goal-driven interactions, CLUs iteratively refine these knowledge spaces, enabling the system to adapt dynamically to complex tasks, extract nuanced insights, and build upon past experiences autonomously. We demonstrate CLUs' effectiveness through a cryptographic reasoning task, where they continuously evolve their understanding through feedback to uncover hidden transformation rules. While conventional models struggle to grasp underlying logic, CLUs excel by engaging in an iterative, goal-oriented process. Specialized components-handling knowledge retrieval, prompt generation, and feedback analysis-work together within a reinforcing feedback loop. This approach allows CLUs to retain the memory of past failures and successes, adapt autonomously, and apply sophisticated reasoning effectively, continually learning from mistakes while also building on breakthroughs.
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。