mlsanityData to 14 Oct 2026

RAM: Towards an Ever-Improving Memory System by Learning from Communications

arXiv 2404.12045 ↗First posted 18 Apr 2024cs.AI cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce an innovative RAG-based framework with an ever-improving memory. Inspired by humans'pedagogical process, RAM utilizes recursively reasoning-based retrieval and experience reflections to continually update the memory and learn from users' communicative feedback, namely communicative learning. Extensive experiments with both simulated and real users demonstrate significant improvements over traditional RAG and self-knowledge methods, particularly excelling in handling false premise and multi-hop questions. Furthermore, RAM exhibits promising adaptability to various feedback and retrieval methods, showcasing its potential for advancing AI capabilities in dynamic knowledge acquisition and lifelong learning.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

35 of 51 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2017Deep reinforcement learning from human preferencescited by 3,912
  8. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  11. 2021Learning to Prompt for Continual Learningcited by 944
  12. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
23 more
  1. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  2. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  3. 2019Three scenarios for continual learningcited by 614
  4. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  7. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 318
  8. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 300
  9. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 202
  10. 2023Don't Make Your LLM an Evaluation Benchmark Cheatercited by 194
  11. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  12. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  13. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 171
  14. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  15. 2023LLM360: Towards Fully Transparent Open-Source LLMscited by 104
  16. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  17. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  18. 2023Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizationscited by 61
  19. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  20. 2021Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedbackcited by 35
  21. 2023Injecting the BM25 Score as Text Improves BERT-Based Re-rankerscited by 17
  22. 2023Gpt-4: A Review on Advancements and Opportunities in Natural Language Processingcited by 15
  23. 2023Hierarchical confusion matrix for classification performance evaluationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Spacecited by 43
  2. 2025ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflectioncited by 12
  3. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  4. 2025Dynamic Affective Memory Management for Personalized LLM Agentscited by 7
  5. 2025TokenSwift: Lossless Acceleration of Ultra Long Sequence Generationcited by 4
  6. 2026SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic Statescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
  2. 2026Towards Autonomous Memory Agents
  3. 2024GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation
  4. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents
  5. 2026Evaluating Memory Structure in LLM Agents
  6. 2025MemOS: A Memory OS for AI System
  7. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
  8. 2026Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems