mlsanityData to 7 Oct 2026

Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline

arXiv 2606.04315 ↗First posted 3 Jun 2026cs.AIcited by 0

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

Abstract (arXiv)

LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (multi-session chat or a single trajectory format), and there is little evidence that they generalize across the heterogeneous trajectories agents encounter in deployment. We revisit eight memory systems plus an agentic harness for search problems, on five scenarios: single-turn QA, multi-session chat, agentic-trajectory QA, memory stress tests, and long-horizon agentic tasks. The harness, which self-manages flat text-file storage via tool calls, achieves the best cross-task ranking, suggesting that memory performance hinges on giving the agent active control over storage and retrieval rather than on a passive store behind a fixed pipeline. We instantiate this insight in AutoMEM, an agentic memory harness with a self-managed tool interface that achieves the best cross-scenario generality among the systems we evaluate.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 43 of its 54 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

43 of 54 references.

Closest ancestors · 13

Same direction, newest first

  1. 2026Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents5 Mar
  2. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications26 Feb
  3. 2026Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents11 Feb
  4. 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents6 Feb
  5. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory5 Feb
  6. 2026Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents14 Jan
  7. 2026SwiftMem: Fast Agentic Memory via Query-aware Indexing13 Jan
  8. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents6 Jan
  9. 2026SimpleMem: Efficient Lifelong Memory for LLM Agents5 Jan
  10. 2025Memory in the Age of AI Agents15 Dec
  11. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  12. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
1 more
  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
18 more
  1. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  3. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  4. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  5. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
  6. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  7. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 235
  8. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  9. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 204
  10. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  11. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 113
  12. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 83
  13. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 56
  14. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interactioncited by 33
  15. 2025REALTALK: A 21-Day Real-World Dataset for Long-Term Conversationcited by 31
  16. 2026REMem: Reasoning with Episodic Memory in Language Agentcited by 20
  17. 2026ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference Systemcited by 17
  18. 2026The Pensieve Paradigm: Stateful Language Models Mastering Their Own Contextcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  2. 2026Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
  3. 2026Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
  4. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  5. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
  6. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  7. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
  8. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents