#memory-systems News & Analysis

30 articles tagged with #memory-systems. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

30 articles

AIBullisharXiv – CS AI · Mar 36/109

🧠

GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation

Researchers introduce GAM-RAG, a training-free framework that improves Retrieval-Augmented Generation by building adaptive memory from past queries instead of relying on static indices. The system uses uncertainty-aware updates inspired by cognitive neuroscience to balance stability and adaptability, achieving 3.95% better performance while reducing inference costs by 61%.

AINeutralarXiv – CS AI · Mar 36/1010

🧠

According to Me: Long-Term Personalized Referential Memory QA

Researchers introduce ATM-Bench, the first benchmark for evaluating AI assistants' ability to recall and reason over long-term personalized memory across multiple modalities. The benchmark reveals poor performance (under 20% accuracy) for current state-of-the-art memory systems, highlighting significant limitations in personalized AI capabilities.

AIBullisharXiv – CS AI · Mar 36/105

🧠

REMem: Reasoning with Episodic Memory in Language Agent

Researchers have developed REMem, a new framework that enables AI language agents to form and reason with episodic memory similar to humans. The system uses a two-phase approach with offline memory graph indexing and online agentic retrieval, showing significant improvements over existing memory systems like Mem0 and HippoRAG 2.

AIBullisharXiv – CS AI · Feb 276/107

🧠

AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications

Researchers introduce AMA-Bench, a new benchmark for evaluating long-horizon memory in AI agents deployed in real-world applications. The study reveals existing memory systems underperform due to lack of causality and objective information, while their proposed AMA-Agent system achieves 57.22% accuracy, surpassing baselines by 11.16%.

AINeutralarXiv – CS AI · Mar 275/10

🧠

A Unified Memory Perspective for Probabilistic Trustworthy AI

Researchers present a unified framework for probabilistic AI computation that treats deterministic and stochastic data access under a common perspective. The study identifies memory systems as performance bottlenecks in trustworthy AI and proposes compute-in-memory approaches to address scalability challenges.

← PrevPage 2 of 2