记忆¶
综述¶
RL¶
通用¶
- 1911.00172_kNN-LMs: Generalization through Memorization: Nearest Neighbor Language Models
- 2304.13343_SCMemory: Enhancing Large Language Model with Self-Controlled Memory Framework
- 2305.11792_Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
- 2305.17144_GITM: Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
- 2306.03901_ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
- 2308.10144_ExpeL: LLM Agents Are Experiential Learners
- 2309.02427_❇️CoALA: Cognitive Architectures for Language Agents
- 2310.08560_MemGPT: Towards LLMs as Operating Systems
- 2311.08719_Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
- 2312.17653_❇️LARP: Language-Agent Role Play for Open-World Games
- 2402.04624_MemoryLLM: Towards Self-Updatable Large Language Models
- 2402.09727_ReadAgent: A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
- 2404.11672_MemLLM: Finetuning LLMs to Use Explicit Read-Write Memory
- 2404.13501_LLM_Agent_Memory_Survey: A Survey on the Memory Mechanism of Large Language Model based Agents
- 2407.01178_❇️Memory3: Language Modeling with Explicit Memory
- 2410.15665_LongTermMemory: The Foundation of AI Self-Evolution
- 2502.00592_M+: Extending MemoryLLM with Scalable Long-Term Memory
- 2502.12110_A-Mem: Agentic Memory for LLM Agents
- 2504.15965_❇️From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
- 2504.19413_❇️Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- 2505.22101_MemOS: An Operating System for Memory-Augmented Generation (MAG) in LLM (Short Version)
- 2506.06326❇️_MemoryOS: Memory OS of AI Agent
- 2505.22101_❇️MemOS: A Memory OS for AI System
- 2508.09874_Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
- 2509.06269_REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents
- 2509.24704_MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
- 2510.18866_❇️LightMem: Lightweight and Efficient Memory-Augmented Generation
- 2512.18746_MemEvolve: Meta-Evolution of Agent Memory Systems
- 2601.02163_EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
通用-Github¶
记忆相关Agent¶
- 2504.10147_PersonalRAG❇️: A Survey of Personalization: From RAG to Agent
- 2506.07398❇️_G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
- 2507.02259_MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
- 2507.07957_MIRIX: Multi-Agent Memory System for LLM-Based Agents
- 2509.25140❇️_ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
记忆相关数据集¶
- 2305.10250_MemoryBank: Enhancing Large Language Models with Long-Term Memory
- 2308.08239_MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
- 2402.17753_LoCoMo❇️: Evaluating Very Long-Term Conversational Memory of LLM Agents
- 2410.10813_LongMemEval: Benchmarking Chat Assist- ants on Long-Term Interactive Memory
- 2506.21605_MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
- 2507.05257_MemoryAgentBench: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- 2510.27246_BEAM: Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
多模态记忆¶
- 2506.05813_MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
- 2508.09736_M3-Agent❇️: Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- 2509.11914_EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
- 2510.12422_VideoLucy: Deep Memory Backtracking for Long Video Understanding
参数记忆¶
- 1907.05242_PKM: Large Memory Layers with Product Keys
- 2305.02437_Selfmem: Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory
- 2407.04153_PEER: Mixture of A Million Experts
- 2412.09764_Memory+: Memory Layers at Scale
- 2508.18756_UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
图结构记忆¶
应用-推荐¶
- Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
- 08xx.xxxxx_SVD++: Factorization meets the neighborhood: a multifaceted collaborative filtering model
- Recommender systems: An overview of different approaches to recommendations
- 1902.07153_SGCN: Simplifying Graph Convolutional Networks
- 1905.08108_NGCF: Neural Graph Collaborative Filtering
- 2001.10167_RGCF: Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
- 2002.02126_LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
- 2010.10783_SGL: Self-supervised Graph Learning for Recommendation
- 2112.08679_SimGCL: Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
- 2202.06200_NCL: Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
- 2203.13366_RLP_P5: A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)
- 2302.08191_LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
- 2303.14524_ChatRec: Towards Interactive and Explainable LLMs-Augmented Recommender System
- 2305.00447_TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
- 2305.07001_InstructRec: Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach
- 2306.10933_KAR: Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models
- 2308.11131_ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
- 2310.15950_RLMRec: Representation Learning with Large Language Models for Recommendation
- 2311.01343_CLLM4Rec: Collaborative Large Language Model for Recommender Systems
- 2502.18965_OneRec: Unifying Retrieve and Rank with Generative Recommender and Preference Alignment
- 2508.20900_OneRec-V2 Technical Report
- 2510.11639_OneRec-Think: In-Text Reasoning for Generative Recommendation
- 2511.11255_Align3GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation