mlsanityData to 14 Oct 2026

Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents

arXiv 2609.23986 ↗First posted 21 Sep 2026cs.AI cs.LGcited by 14

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

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 method, 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× speedup over the fastest competing memory system, and lowering average query latency to 0.93,s, a 36.7% reduction.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 38 of its 49 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

38 of 49 references.

Closest ancestors · 9

Same direction, newest first

  1. 2026Zero-Mem: Zero-Token Memory Operations for LLM Agents31 Jul
  2. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution11 May
  3. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations22 Feb
  4. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents6 Jan
  5. 2026SimpleMem: Efficient Lifelong Memory for LLM Agents5 Jan
  6. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  7. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  8. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  9. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts15 Feb

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  10. 2020Longformer: The Long-Document Transformercited by 3,413
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  12. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
17 more
  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  2. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  3. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  5. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  7. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  10. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  11. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  12. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  13. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  14. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  15. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  16. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  17. 2023System 2 Attention (is something you might need too)cited by 89

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agentscited by 4
  2. 2026Typed Decision Models: An Early Evidence Audit and Evaluation Checklistcited by 3
  3. 2026From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Modelcited by 2
  4. 2026Mnemon: Raw Records, Fast Judgments, Slow Thoughtscited by 2
  5. 2026When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Modelcited by 1
  6. 2026Benchmarking System One decision models against trained classifiers and language models for automated decision gatescited by 1
  7. 2026Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Usecited by 1
  8. 2026OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System Onecited by 0
  9. 2026Jev-IDS: System One Models for Network Intrusion Detectioncited by 0
  10. 2026Decide Before You Look: Learning Which Retrieved Memories Deserve Pixelscited by 0
  11. 2026Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Laborcited by 0
  12. 2026Can Jev be Your Q or Policy in Reinforcement Learning?cited by 0
2 more
  1. 2026Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gatecited by 0
  2. 2026JevGPT: Thinking Fast and Slow in Autonomous Researchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  2. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  3. 2026MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
  4. 2026Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
  5. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  6. 2026MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
  7. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents
  8. 2026Hippocampus: An Efficient and Scalable Memory Module for Agentic AI