Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
cs.AI, cs.LG
Submitted: 2026-09-21
Updated: 2026-09-21
Code: https://github.com/libingzheren/Jev-Mem
License: http://creativecommons.org/licenses/by/4.0/
The gist: Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive
Terminology
Abstract
Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs to control how memories are organized, retrieved, and used, placing expensive generation on the critical path of memory operations. We introduce, a new agentic memory architecture inspired by System-One/System-Two cognition. System One captures fast, lightweight decision-making, whereas System Two performs slower, deliberative reasoning. Jev-Mem brings this division of labor to agentic memory through a dedicated System-One control plane, a structured multi-relational memory plane, and a System-Two reasoning plane. The System-One controller governs memory typing and relational organization during construction, and dynamically performs query routing, retrieval-budget allocation, graph traversal, candidate scoring, and adaptive stopping during retrieval. System Two is invoked only for complex reasoning and answer synthesis. This design improves both memory effectiveness and system efficiency: on LoCoMo Jev-Mem achieves an overall LLM-as-a-Judge score of 0.777, an 11.0% relative improvement over the strongest baseline, while reducing memory construction time to 158,s, a 6.6 times speedup over the fastest competing memory system, and lowering average query latency to 0.93,s, a 36.7% reduction.
Sources
- GPT-4 Technical Report
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Longformer: The Long-Document Transformer
- Improving language models by retrieving from trillions of tokens
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- REALM: Retrieval-Augmented Language Model Pre-Training
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Atlas: Few-shot Learning with Retrieval Augmented Language Models
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
- Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
- Memory OS of AI Agent
- A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
- Fast Inference from Transformers via Speculative Decoding
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- What Deserves Memory: Adaptive Memory Distillation for LLM Agents
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection