AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Control
cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/UnicusT11/AMU-memory
Terminology
Sources
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- The Llama 3 Herd of Models
- RET-LLM: Towards a General Read-Write Memory for Large Language Models
- WebGPT: Browser-assisted question-answering with human feedback
- GPT-4 Technical Report
- MemGPT: Towards LLMs as Operating Systems
- User Modeling and User Profiling: A Comprehensive Survey
- REPLUG: Retrieval-Augmented Black-Box Language Models
- BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
- Preference-Aware Memory Update for Long-Term LLM Agents
- Gemini: A Family of Highly Capable Multimodal Models
- Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
- Adaptive Memory Admission Control for LLM Agents
- Lightweight LLM Agent Memory with Small Language Models
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
- Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
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