A Controlled Audit of Personal AI Memory for Rating Prediction
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/shi1720/personal-ai-memory-studies
Sources
- Memory Assisted LLM for Personalized Recommendation System
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability
- MemRerank: Preference Memory for Personalized Product Reranking
- Can Large Language Models Understand Preferences in Personalized Recommendation?
- MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
- Language-Based User Profiles for Recommendation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks