paper-with-me

Papers

AI-native Memory: A Pathway from LLMs Towards AGI

2024-06-26 · Jingbo Shang, Zai Zheng, Jiale Wei, Xiang Ying, Felix Tao, Mindverse Team

Large language models (LLMs) have demonstrated the world with the sparks of artificial general intelligence (AGI). One opinion, especially from some startups working on LLMs, argues that an LLM with nearly unlimited context length can realize AGI. However, they might be too optimistic about the long-context capability of (existing) LLMs -- (1) Recent literature has shown that their effective context length is significantly smaller than their claimed context length; and (2) Our reasoning-in-a-haystack experiments further demonstrate that simultaneously finding the relevant information from a long context and conducting (simple) reasoning is nearly impossible. In this paper, we envision a pathway from LLMs to AGI through the integration of \emph{memory}. We believe that AGI should be a system where LLMs serve as core processors. In addition to raw data, the memory in this system would store a large number of important conclusions derived from reasoning processes. Compared with retrieval-augmented generation (RAG) that merely processing raw data, this approach not only connects semantically related information closer, but also simplifies complex inferences at the time of querying. As an intermediate stage, the memory will likely be in the form of natural language descriptions, which can be directly consumed by users too. Ultimately, every agent/person should have its own large personal model, a deep neural network model (thus \emph{AI-native}) that parameterizes and compresses all types of memory, even the ones cannot be described by natural languages. Finally, we discuss the significant potential of AI-native memory as the transformative infrastructure for (proactive) engagement, personalization, distribution, and social in the AGI era, as well as the incurred privacy and security challenges with preliminary solutions.

📄 PDF Abstract BibTeX arXiv:2406.18312

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs

2026-08-31 · Shuyao Xiao, Shengling Wang, Xuan Chen, Ke Chao 외 arxiv

Long-term memory enables large language models (LLMs) to preserve and reuse information across interactions, but it can also turn localized errors into persistent risks. Existing work mainly evaluates whether memory syst…

DART: Distilling Autoregressive Reasoning to Silent Thought

2025-06-13 · Nan Jiang, Ziming Wu, De-Chuan Zhan, Fuming Lai 외

Chain-of-Thought (CoT) reasoning has significantly advanced Large Language Models (LLMs) in solving complex tasks. However, its autoregressive paradigm leads to significant computational overhead, hindering its deploymen…

Agentic Unlearning: When LLM Agent Meets Machine Unlearning

2026-02-06 · Bin Wang, Fan Wang, Pingping Wang, Jinyu Cong 외 arxiv

In this paper, we introduce \textbf{agentic unlearning} which removes specified information from both model parameters and persistent memory in agents with closed-loop interaction. Existing unlearning methods target para…

VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse

2025-12-16 · Ying Nie, Kai Han, Hongguang Li, Hang Zhou 외 arxiv

The rapid scaling of Large Language Models (LLMs) has achieved remarkable performance, but it also leads to prohibitive memory costs. Existing parameter-efficient approaches such as pruning and quantization mainly compre…

MuonSSM: Orthogonalizing State Space Models for Sequence Modeling

2026-06-29 · Thai-Khanh Nguyen, Ngoc-Bich-Uyen Vo, Thieu N. Vo, Tan M. Nguyen 외 arxiv

State space models (SSMs) have emerged as efficient linear-time alternatives to attention for long-sequence modeling. However, existing SSMs often suffer from instability and memory degradation over extended horizons due…