让大模型持续学习新任务，还能记住旧知识。
The Self-Learning Agent with a Progressive Neural Network Integrated Transformer
- 用动态数据收集+小样本微调实现持续学习
- 在多个任务上保持高适应性与记忆稳定性
- 适合需要长期演进的智能对话与编程系统
本文提出一种自学习智能体，将 LLaMA 3.2 与渐进式神经网络（PNN）结合，用于对话AI和代码生成的持续学习。该框架能动态收集数据，以极少样本完成任务微调，并利用元学习实现快速适应。通过LoRA优化微调过程，EWC增强知识保留能力。实验表明，该方法显著提升了模型的适应性与记忆稳定性，为实现通用人工智能（AGI）提供了可扩展的解决方案。
原文摘要 · Abstract (English)
This paper introduces a self-learning agent that integrates LLaMA 3.2 with a Progressive Neural Network (PNN) for continual learning in conversational AI and code generation. The framework dynamically collects data, fine-tunes tasks with minimal samples, and leverages Meta-Learning for rapid adaptation. LoRA optimizes fine-tuning, while Elastic Weight Consolidation (EWC) enhances knowledge retention. Experimental results demonstrate improved adaptability and memory stability, positioning this approach as a scalable step toward Artificial General Intelligence (AGI).
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。