MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
YuFei Luo, Xiucheng Xu, Zhen Yang
cs.AI, cs.CL
Submitted: 2026-08-03
Comments: Submitted to AAAI 2027. 19 pages, 10 figures, 18 tables
Code: https://github.com/luoyufeihaha/MemSIF
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- WritePolicyBench: Benchmarking Memory Write Policies under Byte Budgets
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- The Llama 3 Herd of Models
- Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
- A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
- GPT-4o System Card
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
- Structured Episodic Event Memory
- RET-LLM: Towards a General Read-Write Memory for Large Language Models
- MemGPT: Towards LLMs as Operating Systems
- Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents
- MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
- Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
- SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- GAM: Hierarchical Graph-based Agentic Memory for LLM Agents
- Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection