mlsanityData to 7 Oct 2026

TeleMem: Building Long-Term and Multimodal Memory for Agentic AI

arXiv 2601.06037 ↗First posted 12 Dec 2025cs.CL cs.AI cs.CVcited by 14

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable mechanisms for updating or refining stored memories, leading to schema-driven hallucinations, inefficient write operations, and minimal support for multimodal reasoning.To address these challenges, we propose TeleMem, a unified long-term and multimodal memory system that maintains coherent user profiles through narrative dynamic extraction, ensuring that only dialogue-grounded information is preserved. TeleMem further introduces a structured writing pipeline that batches, retrieves, clusters, and consolidates memory entries, substantially improving storage efficiency, reducing token usage, and accelerating memory operations. Additionally, a multimodal memory module combined with ReAct-style reasoning equips the system with a closed-loop observe, think, and act process that enables accurate understanding of complex video content in long-term contexts. Experimental results show that TeleMem surpasses the state-of-the-art Mem0 baseline with 19% higher accuracy, 43% fewer tokens, and a 2.1x speedup on the ZH-4O long-term role-play gaming benchmark.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 41 of its 47 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

41 of 47 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory11 Nov
  2. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning3 Nov
  3. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agents25 Sep
  4. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agents5 Aug
  5. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul
  6. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems9 Jun
  7. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  8. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  9. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  10. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 31

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2024GPT-4o System Cardcited by 4,467
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  6. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  7. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agentcited by 323
  8. 2022Transformer Memory as a Differentiable Search Indexcited by 242
  9. 2023Augmenting Language Models with Long-Term Memorycited by 186
  10. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  11. 2025MemOS: A Memory OS for AI Systemcited by 129
  12. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 117
19 more
  1. 2025A Comprehensive Survey on Long Context Language Modelingcited by 113
  2. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  3. 2025Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understandingcited by 94
  4. 2025Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memorycited by 88
  5. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  6. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  7. 2024Personalized LLM Response Generation with Parameterized Memory Injectioncited by 33
  8. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  9. 2025MemVerse: Multimodal Memory for Lifelong Learning Agentscited by 31
  10. 2025HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understandingcited by 19
  11. 2025MLP Memory: A Retriever-Pretrained Memory for Large Language Modelscited by 19
  12. 2025Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoningcited by 10
  13. 2025GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understandingcited by 9
  14. 2025MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialoguescited by 8
  15. 2025D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Treecited by 7
  16. 2025Everything is Context: Agentic File System Abstraction for Context Engineeringcited by 6
  17. 2024Generation with Dynamic Vocabularycited by 5
  18. 2025Protein Design with Dynamic Protein Vocabularycited by 5
  19. 2025TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  2. 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkcited by 16
  3. 2026GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)cited by 10
  4. 2026MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agentscited by 9
  5. 2026Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baselinecited by 8
  6. 2026Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representationcited by 5
  7. 2026Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMscited by 2
  8. 2026Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrievalcited by 2
  9. 2026HippoCamp: Benchmarking Contextual Agents on Personal Computerscited by 1
  10. 2026Task-Focused Memorization for Multimodal Agentscited by 1
  11. 2026MemPose: Category-level Object Pose Estimation with Memorycited by 1
  12. 2026Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agentscited by 1
2 more
  1. 2026EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Taskscited by 0
  2. 2026Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
  2. 2026Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
  3. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
  4. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  5. 2026EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memory
  6. 2026H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions
  7. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
  8. 2026MemFit: Efficient Long-Term Agentic Memory