# REMem: Reasoning with Episodic Memory in Language Agent

arXiv: https://arxiv.org/abs/2602.13530 · HTML: https://mlsanity.com/paper/2602.13530/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [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)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments](https://mlsanity.com/paper/2402.14672/) (2024)
- [REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation](https://mlsanity.com/paper/2502.13270/) (2025)
- [TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues](https://mlsanity.com/paper/2502.01630/) (2025)
- [Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning](https://mlsanity.com/paper/2311.09821/) (2023)
- [MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models](https://mlsanity.com/paper/2310.05157/) (2023)
- [Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models](https://mlsanity.com/paper/2504.05258/) (2025)

## Built on by (most cited first, 23 of 23)

- [GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents](https://mlsanity.com/paper/2606.18829/) (2026)
- [Choosing How to Remember: Adaptive Memory Structures for LLM Agents](https://mlsanity.com/paper/2602.14038/) (2026)
- [Self-GC: Self-Governing Context for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.00692/) (2026)
- [Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory](https://mlsanity.com/paper/2606.10677/) (2026)
- [RaMem: Contextual Reinstatement for Long-term Agentic Memory](https://mlsanity.com/paper/2606.22844/) (2026)
- [From History to State: Constant-Context Skill Learning for LLM Agents](https://mlsanity.com/paper/2605.05413/) (2026)
- [MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems](https://mlsanity.com/paper/2605.18565/) (2026)
- [HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling](https://mlsanity.com/paper/2602.13933/) (2026)
- [MemTrace: Probing What Final Accuracy Misses in Long-Term Memory](https://mlsanity.com/paper/2606.17328/) (2026)
- [RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory](https://mlsanity.com/paper/2608.13334/) (2026)
- [MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare](https://mlsanity.com/paper/2605.11814/) (2026)
- [Tree-based Credit Assignment for Multi-Agent Memory System](https://mlsanity.com/paper/2605.04811/) (2026)
- [Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.11813/) (2026)
- [DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory](https://mlsanity.com/paper/2605.22411/) (2026)
- [Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline](https://mlsanity.com/paper/2606.04315/) (2026)
- [Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents](https://mlsanity.com/paper/2609.11060/) (2026)
- [Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness](https://mlsanity.com/paper/2606.10413/) (2026)
- [Situation Perception: A Necessary Primitive to Artificial Superintelligence](https://mlsanity.com/paper/2606.30481/) (2026)
- [Unified Agent: Managing Interactions across Devices](https://mlsanity.com/paper/2608.05729/) (2026)
- [LivingRAG: Augmenting Graph RAG with Experience](https://mlsanity.com/paper/2608.25960/) (2026)
- [PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation](https://mlsanity.com/paper/2610.04916/) (2026)
- [ExperienceIndex: Artifact-Grounded Memory](https://mlsanity.com/paper/2610.10091/) (2026)
- [Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence](https://mlsanity.com/paper/2610.20312/) (2026)

## Abstract (arXiv)

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current agents are not yet capable of effectively recollecting and reasoning over interaction histories. We identify and formalize the core challenges of episodic recollection and reasoning from this gap, and observe that existing work often overlooks episodicity, lacks explicit event modeling, or overemphasizes simple retrieval rather than complex reasoning. We present REMem, a two-phase framework for constructing and reasoning with episodic memory: 1) Offline indexing, where REMem converts experiences into a hybrid memory graph that flexibly links time-aware gists and facts. 2) Online inference, where REMem employs an agentic retriever with carefully curated tools for iterative retrieval over the memory graph. Comprehensive evaluation across four episodic memory benchmarks shows that REMem substantially outperforms state-of-the-art memory systems such as Mem0 and HippoRAG 2, showing 3.4% and 13.4% absolute improvements on episodic recollection and reasoning tasks, respectively. Moreover, REMem also demonstrates more robust refusal behavior for unanswerable questions.