الملخص
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. \textbf{In-parameter memory} offers a complementary substrate: reusable memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric memory at deployment: a memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: \textbf{Parameter Placement}, which includes Embedding, Attention, FFN layers, or Hybrid when two or more layers are used; and \textbf{Parameter Acquisition Time}, which distinguishes methods whose memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Huang, H., Xie, Z., Bai, J., Gao, Y., Tsang, H. T., Song, W., Jing, H., Li, Y., & Song, Y. (2026). Towards In-Parameter Memory Augmentation for Large Language Models. https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models
MLA 9
Huang, Haoyu, et al. "Towards In-Parameter Memory Augmentation for Large Language Models." https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models.
شيكاغو (المؤلف–التاريخ)
Huang, Haoyu, Zhongwei Xie, Jiaxin Bai, Yisen Gao, Hong Ting Tsang, Wuganjing Song, Huihao Jing, Yufei Li, and Yangqiu Song. 2026. "Towards In-Parameter Memory Augmentation for Large Language Models." https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models.
هارفارد
Huang, H., Xie, Z., Bai, J., Gao, Y., Tsang, H. T., Song, W., Jing, H., Li, Y. and Song, Y. (2026) 'Towards In-Parameter Memory Augmentation for Large Language Models', Available at: https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models.
فانكوفر
Huang H, Xie Z, Bai J, Gao Y, Tsang HT, Song W, et al. Towards In-Parameter Memory Augmentation for Large Language Models. https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models
IEEE
H. Huang, Z. Xie, J. Bai, Y. Gao, H. T. Tsang, W. Song, H. Jing, Y. Li, and Y. Song, "Towards In-Parameter Memory Augmentation for Large Language Models," https://omanscience.com/ar/articles/towards-in-parameter-memory-augmentation-for-large-language-models.