mlsanityData to 14 Oct 2026

SGMem: Sentence Graph Memory for Long-Term Conversational Agents

arXiv 2509.21212 ↗First posted 25 Sep 2025cs.CL cs.IRcited by 29

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

Abstract (arXiv)

Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods based on fact extraction or summarization reduce redundancy but struggle to organize and retrieve relevant information across different granularities of dialogue and generated memory. We introduce SGMem (Sentence Graph Memory), which represents dialogue as sentence-level graphs within chunked units, capturing associations across turn-, round-, and session-level contexts. By combining retrieved raw dialogue with generated memory such as summaries, facts and insights, SGMem supplies LLMs with coherent and relevant context for response generation. Experiments on LongMemEval and LoCoMo show that SGMem consistently improves accuracy and outperforms strong baselines in long-term conversational question answering.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 25 of its 41 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

25 of 41 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Memory OS of AI Agent30 May
  2. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents26 May
  3. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior21 May
  4. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents11 Mar
  5. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  6. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  7. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  8. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 17

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  3. 2024A Survey on LLM-as-a-Judgecited by 1,423
  4. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  5. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  6. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  7. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  8. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  9. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  10. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  11. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 127
  12. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 124
5 more
  1. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  2. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 105
  3. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  4. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  5. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 25.

29 papers.

Sort:

By area:

  1. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 25
  2. 2025A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agentscited by 21
  3. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  4. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  5. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 18
  6. 2026Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoningcited by 17
  7. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AIcited by 14
  8. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 14
  9. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  10. 2026MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolutioncited by 12
  11. 2026Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memorycited by 10
  12. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agentscited by 7
17 more
  1. 2026GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoningcited by 6
  2. 2026ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agentscited by 4
  3. 2026HyMem: Hybrid Memory Architecture with Dynamic Retrieval Schedulingcited by 4
  4. 2026MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Modelscited by 3
  5. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memorycited by 2
  6. 2026PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agentscited by 2
  7. 2026MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrievalcited by 1
  8. 2026G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agentscited by 1
  9. 2026Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMscited by 1
  10. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agentscited by 1
  11. 2026AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMscited by 1
  12. 2026Proactive Memory for Ad-Hoc Recall over Streaming Dialoguescited by 0
  13. 2026Improving Multi-turn Dialogue Consistency with Self-Recall Thinkingcited by 0
  14. 2026Experience Memory Graph: One-Shot Error Correction for Agentscited by 0
  15. 2026FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialoguecited by 0
  16. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluationcited by 0
  17. 2026Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
  3. 2026DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
  4. 2026AgenticAI-DialogGen: Topic-Guided Conversation Generation for Fine-Tuning and Evaluating Short- and Long-Term Memories of LLMs
  5. 2026HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
  6. 2026AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
  7. 2026Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
  8. 2026Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents