Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
cs.CL
Submitted: 2026-10-08
Updated: 2026-10-08
Terminology
Sources
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
- MemGPT: Towards LLMs as Operating Systems
- FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval
- SGMem: Sentence Graph Memory for Long-Term Conversational Agents
- A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
- Graph-based Agent Memory: Taxonomy, Techniques, and Applications
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Qwen3 Technical Report
- The Llama 3 Herd of Models
- Memory in the Age of AI Agents
- Augmenting Language Models with Long-Term Memory
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- A-MEM: Agentic Memory for LLM Agents
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
- GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
- HyperMem: Hypergraph Memory for Long-Term Conversations
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering