Skip to content
gentic.news — AI News Intelligence Platform

memory systems

30 articles about memory systems in AI news

Beyond RAG: How AI Memory Systems Are Creating Truly Adaptive Agents

AI development is shifting from static retrieval systems to dynamic memory architectures that enable continual learning. This evolution from RAG to agent memory represents a fundamental change in how AI systems accumulate and utilize knowledge over time.

85% relevant

Memory Systems for AI Agents: Architectures, Frameworks, and Challenges

A technical analysis details the multi-layered memory architectures—short-term, episodic, semantic, procedural—required to transform stateless LLMs into persistent, reliable AI agents. It compares frameworks like MemGPT and LangMem that manage context limits and prevent memory drift.

95% relevant

Hindsight AI: How Biomimetic Memory Systems Are Revolutionizing Agent Intelligence

Hindsight, an open-source AI memory system, achieves state-of-the-art performance on the LongMemEval benchmark by mimicking human memory structures. Unlike traditional RAG approaches, it employs parallel retrieval strategies to enable agents that don't just remember—they learn.

95% relevant

AI Agents Get a Memory Upgrade: New Framework Treats Multi-Agent Memory as Computer Architecture

A new paper proposes treating multi-agent memory systems as a computer architecture problem, introducing a three-layer hierarchy and identifying critical protocol gaps. This approach could significantly improve reasoning, skills, and tool usage in collaborative AI systems.

85% relevant

Microsoft's CORPGEN Framework: The Missing Link for Enterprise AI Agents

Microsoft Research introduces CORPGEN, a breakthrough framework enabling AI agents to manage complex, multi-horizon organizational tasks through hierarchical planning and memory systems. This addresses critical failure modes that have limited autonomous agents in real corporate environments.

75% relevant

How a 50-Year-Old Computer Science Concept Just Outperformed Anthropic's Claude Code

A small startup has outperformed Anthropic's flagship Claude Code using a novel architecture based on persistent memory systems. This breakthrough demonstrates how classic computer science principles can solve modern AI limitations in context retention and reasoning.

70% relevant

OpenSage: The Dawn of Self-Programming AI Agents That Build Their Own Teams

OpenSage introduces the first agent development kit enabling LLMs to autonomously create AI agents with self-generated architectures, toolkits, and memory systems, potentially revolutionizing how AI systems are designed and deployed.

75% relevant

The Unix Philosophy Returns: How File Systems Could Solve AI's Memory Crisis

A new research paper proposes treating AI context management like a Unix file system, with OpenClaw demonstrating that storing memory, tools, and knowledge as files creates traceable, auditable AI systems. This approach could solve fragmentation and transparency issues plaguing current agent frameworks.

85% relevant

Nous Research's Hermes Agent Features Self-Improving Skills, Persistent Memory

A new evaluation of Nous Research's Hermes Agent highlights its self-improving ability to build reusable tools from experience and a smarter persistent memory system that conserves token usage. The agent reportedly improves with continued use, representing a shift towards more adaptive AI systems.

85% relevant

Memory Sparse Attention (MSA) Achieves 100M Token Context with Near-Linear Complexity

A new attention architecture, Memory Sparse Attention (MSA), breaks the 100M token context barrier while maintaining 94% accuracy at 1M tokens. It uses document-wise RoPE and end-to-end sparse attention to outperform RAG systems and frontier models.

95% relevant

Alibaba DAMO Academy Releases AgentScope: A Python Framework for Multi-Agent Systems with Visual Design

Alibaba's DAMO Academy has open-sourced AgentScope, a Python framework for building coordinated AI agent systems with visual design, MCP tools, memory, RAG, and reasoning. It provides a complete architecture rather than just building blocks.

97% relevant

AI Agents Get a Memory Upgrade: New Research Tackles Long-Horizon Task Challenges

Researchers have developed new methods to scale AI agent memory for complex, long-horizon tasks. The breakthrough addresses one of the biggest limitations in current agent systems—their inability to retain and utilize information over extended sequences of actions.

87% relevant

The File Paradigm: How Simple File Systems Could Revolutionize AI Context Management

New research proposes treating all AI context as files within a unified system, potentially solving memory and organization challenges in complex AI workflows. This approach could dramatically simplify how AI systems access and manage information.

85% relevant

Memory Sparse Attention (MSA) Enables 100M Token Context Windows with Minimal Performance Loss

Memory Sparse Attention (MSA) is a proposed architecture that allows AI models to store and reason over massive long-term memory directly within their attention mechanism, eliminating the need for external retrieval systems. The approach reportedly enables context windows of up to 100 million tokens with minimal performance degradation.

85% relevant

Stateless Memory for Enterprise AI Agents: Scaling Without State

The paper replaces stateful agent memory with immutable decision logs using event-sourcing, allowing thousands of concurrent agent instances to scale horizontally without state bottlenecks.

85% relevant

Aehr Test Systems Lands $41M AI Chip Order; H2 Bookings Top $92M

Aehr Test Systems received a record $41 million production order from a key hyperscale AI customer. Total bookings for the second half of its fiscal year exceeded $92 million, highlighting surging demand for semiconductor test and burn-in equipment.

74% relevant

Microsoft's MEMENTO Method Reduces LLM Reasoning Memory by 3x

Microsoft researchers introduced MEMENTO, a method where LLMs generate structured 'notes' during multi-step reasoning, reducing the memory footprint of the reasoning process by 3x while maintaining performance. This addresses a key bottleneck in deploying complex reasoning models.

80% relevant

Google's Memory Caching Bridges RNN-Transformer Gap with O(NL) Complexity

Google's 'Memory Caching' method saves RNN memory states at segment boundaries, allowing tokens to reference past checkpoints. This O(NL) approach significantly improves RNN performance on recall tasks, narrowing the gap with Transformers.

95% relevant

Cognee Open-Source Framework Unifies Vector, Graph, and Relational Memory for AI Agents

Developer Akshay Pachaar argues AI agent memory requires three data stores—vector, graph, and relational—to handle semantics, relationships, and provenance. His open-source project Cognee unifies them behind a simple API.

87% relevant

Claude-Mem Plugin Adds Persistent Memory to Claude Code, Cuts Token Use 10x

Developer Akshay Pachaar released Claude-Mem, a free plugin that adds persistent memory across Claude Code sessions. It captures tool usage and implements a 3-layer retrieval system, saving up to 10x tokens.

85% relevant

Karpathy's LLM Wiki Hits 5k Stars, Gains Memory Lifecycle Extension

Andrej Karpathy's LLM Wiki repository gained 5,000 GitHub stars in two days. A developer has now extended it with memory lifecycle features, addressing a noted gap.

77% relevant

Mind: Open-Source Persistent Memory for AI Coding Agents

An open-source tool called Mind creates a shared memory layer for AI coding agents, allowing them to remember project context across sessions and different interfaces like Claude Code, Cursor, and Windsurf.

85% relevant

Engramme Building 'Large Memory Models' to Surface Personal Context

Engramme, founded by Gabriel Kreiman, is developing 'Large Memory Models' (LMMs) designed to connect to a user's digital life and surface relevant context without explicit prompting. The goal is to augment human memory by making personal data available at the right moment.

85% relevant

MIA Framework Boosts GPT-5.4 by 9% on LiveVQA with Bidirectional Memory

Researchers introduced Memory Intelligence Agent (MIA), a framework combining parametric and non-parametric memory with test-time learning. It boosts GPT-5.4 by up to 9% on LiveVQA and achieves 31% average improvement across 11 benchmarks.

99% relevant

Snapchat Details Production Use of Semantic IDs for Recommender Systems

A technical paper from Snapchat details their application of Semantic IDs (SIDs) in production recommender systems. SIDs are ordered lists of codes derived from item semantics, offering smaller cardinality and semantic clustering than atomic IDs. The team reports overcoming practical challenges to achieve positive online metrics impact in multiple models.

90% relevant

OpenAI Reallocates Compute and Talent Toward 'Automated Researchers' and Agent Systems

OpenAI is reallocating significant compute resources and engineering talent toward developing 'automated researchers' and agent-based systems capable of executing complex tasks end-to-end, signaling a strategic pivot away from some existing projects.

89% relevant

Google DeepMind Maps Six 'AI Agent Traps' That Can Hijack Autonomous Systems in the Wild

Google DeepMind has published a framework identifying six categories of 'traps'—from hidden web instructions to poisoned memory—that can exploit autonomous AI agents. This research provides the first systematic taxonomy for a growing attack surface as agents gain web access and tool-use capabilities.

95% relevant

MemFactory Framework Unifies Agent Memory Training & Inference, Reports 14.8% Gains Over Baselines

Researchers introduced MemFactory, a unified framework treating agent memory as a trainable component. It supports multiple memory paradigms and shows up to 14.8% relative improvement over baseline methods.

97% relevant

Throughput Optimization as a Strategic Lever in Large-Scale AI Systems

A new arXiv paper argues that optimizing data pipeline and memory throughput is now a strategic necessity for training large AI models, citing specific innovations like OVERLORD and ZeRO-Offload that deliver measurable efficiency gains.

88% relevant

Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems

New arXiv research proposes transforming static, multi-stage recommendation pipelines into self-evolving 'Agentic Recommender Systems' where modules become autonomous agents. This paradigm shift aims to automate system improvement using RL and LLMs, moving beyond manual engineering.

94% relevant