EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory
cs.AI, cs.CL
Submitted: 2026-09-23
Updated: 2026-09-27
Comments: 25 pages, preprint
Code: https://github.com/RamonMeng/EnSIMem
License: http://creativecommons.org/licenses/by/4.0/
The gist: An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history.
Terminology
Abstract
An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memory systems often compress interactions into generic summaries or retrieve anonymous text chunks, making it difficult for an agent to identify the correct entity, property, and supporting evidence. We present EnSIMem, an entity-structured long-term memory architecture for an agent. During offline construction, the system organizes interactions into theme-coherent episodes and builds dialogue-grounded index entries of the form [entity][entity type][property: value]. Each entry preserves its source turns, temporal information, and available multimodal fields. During online interaction, the agent's request is decomposed into evidence requirements whose properties are aligned with the memory index. Entity-property lookup and adaptive retrieval then collect the evidence needed for point, temporal, compositional, and aggregation reasoning. The agent generates its response from the preserved source evidence rather than from lossy memory summaries. On long-term agent-memory benchmarks, EnSIMem achieves high answer accuracy while maintaining compact, evidence-focused contexts. These results show that entity-structured indexing and episode-level provenance provide a reliable foundation for long-term memory in agents. The code of our model is available at https://github.com/RamonMeng/EnSIMem.
Sources
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- GRAG: Graph Retrieval-Augmented Generation
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- Memory OS of AI Agent
- MemGPT: Towards LLMs as Operating Systems
- Structure-Augmented Reasoning Generation
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
- A-MEM: Agentic Memory for LLM Agents
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems