Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence
cs.CV, cs.AI, cs.CL, cs.IR, cs.LG
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- MemGPT: Towards LLMs as Operating Systems
- FigureQA: An Annotated Figure Dataset for Visual Reasoning
- Longformer: The Long-Document Transformer
- Generating Long Sequences with Sparse Transformers
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
- Extending Context Window of Large Language Models via Positional Interpolation
- LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
- ReAct: Synergizing Reasoning and Acting in Language Models
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Corrective Retrieval Augmented Generation
- Memory Networks
- MEMORYLLM: Towards Self-Updatable Large Language Models
- GAAMA: Graph Augmented Associative Memory for Agents
- Agent Workflow Memory
- Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
- Cognitive Architectures for Language Agents
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models