MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
- Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
- From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
- FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents
- MemGPT: Towards LLMs as Operating Systems
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- A-MEM: Agentic Memory for LLM Agents
- MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
- LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
- Latent Context Compilation: Distilling Long Context into Compact Portable Memory
- LatentPress: Context Compression Beyond Text and Vision
- NextMem: Towards Latent Factual Memory for LLM-based Agents
- Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference
- LatentMem: Customizing Latent Memory for Multi-Agent Systems
- ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
- Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
- LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
- CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
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