# MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents

arXiv: https://arxiv.org/abs/2512.20237 · HTML: https://mlsanity.com/paper/2512.20237/

## Key facts

- Cited by 19 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [Cartridges: Lightweight and general-purpose long context representations via self-study](https://mlsanity.com/paper/2506.06266/) (2025)
- [Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics](https://mlsanity.com/paper/2505.00675/) (2025)
- [FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.22344/) (2025)

## Built on by (most cited first, 19 of 19)

- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents](https://mlsanity.com/paper/2601.02845/) (2026)
- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://mlsanity.com/paper/2604.21748/) (2026)
- [From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents](https://mlsanity.com/paper/2602.17913/) (2026)
- [Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents](https://mlsanity.com/paper/2603.19935/) (2026)
- [Choosing How to Remember: Adaptive Memory Structures for LLM Agents](https://mlsanity.com/paper/2602.14038/) (2026)
- [RaMem: Contextual Reinstatement for Long-term Agentic Memory](https://mlsanity.com/paper/2606.22844/) (2026)
- [AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2603.03290/) (2026)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [PATH-Bench: Path-Dependent Evaluation of Lifelong Agents](https://mlsanity.com/paper/2608.01149/) (2026)
- [MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory](https://mlsanity.com/paper/2605.07242/) (2026)
- [Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents](https://mlsanity.com/paper/2609.16053/) (2026)
- [RAG without Forgetting: Continual Query-Infused Key Memory](https://mlsanity.com/paper/2602.05152/) (2026)
- [MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents](https://mlsanity.com/paper/2605.27437/) (2026)
- [NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents](https://mlsanity.com/paper/2609.33379/) (2026)
- [PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use](https://mlsanity.com/paper/2609.34526/) (2026)
- [Remember Before You're Asked: MemDream for Self-Probing Memory Evolution](https://mlsanity.com/paper/2609.34545/) (2026)
- [Recall What Is Missing: Composing Evidence from Long-Term Agent Memory](https://mlsanity.com/paper/2610.15642/) (2026)

## 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.