mlsanityData to 7 Oct 2026

MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents

arXiv 2512.20237 ↗First posted 23 Dec 2025cs.AIcited by 17

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Memory systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop control of memory retrieval. From this observation, we build memory retrieval as an autonomous, accurate, and compatible agent system, named MemR3, which has two core mechanisms: 1) a router that selects among retrieve, reflect, and answer actions to optimize answer quality; 2) a global evidence-gap tracker that explicitly renders the answering process transparent and tracks the evidence collection process. This design departs from the standard retrieve-then-answer pipeline by introducing a closed-loop control mechanism that enables autonomous decision-making. Empirical results on the LoCoMo benchmark demonstrate that MemR3 surpasses strong baselines on LLM-as-a-Judge score, and particularly, it improves existing retrievers across four categories with an overall improvement on RAG (+7.29%) and Zep (+1.94%) using GPT-4.1-mini backend, offering a plug-and-play controller for existing memory stores.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 20 of its 27 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

20 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics1 May

Other references · 19

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  12. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
7 more
  1. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  2. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  3. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
  4. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 129
  5. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  6. 2025Cartridges: Lightweight and general-purpose long context representations via self-studycited by 74
  7. 2025FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 17.

17 papers.

Sort:

By area:

  1. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  2. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 26
  3. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 19
  4. 2026From Lossy to Verified: A Provenance-Aware Tiered Memory for Agentscited by 16
  5. 2026Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agentscited by 12
  6. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agentscited by 10
  7. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  8. 2026AriadneMem: Threading the Maze of Lifelong Memory for LLM Agentscited by 4
  9. 2026GUI Agents with Reinforcement Learning: Toward Digital Inhabitantscited by 3
  10. 2026Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agentscited by 2
  11. 2026MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memorycited by 1
  12. 2026PATH-Bench: Path-Dependent Evaluation of Lifelong Agentscited by 1
5 more
  1. 2026RAG without Forgetting: Continual Query-Infused Key Memorycited by 0
  2. 2026MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agentscited by 0
  3. 2026NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agentscited by 0
  4. 2026PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Usecited by 0
  5. 2026Remember Before You're Asked: MemDream for Self-Probing Memory Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MemRetriever: Learning to Search, Reflect, and Retrieve from Long-Term Memory ↗
  2. 2026MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
  3. 2026D-Mem: A Dual-Process Memory System for LLM Agents
  4. 2024On the Structural Memory of LLM Agents
  5. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  6. 2026MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
  7. 2026Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
  8. 2026H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure