# Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory

arXiv: https://arxiv.org/abs/2602.15313 · HTML: https://mlsanity.com/paper/2602.15313/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [On Memory Construction and Retrieval for Personalized Conversational Agents](https://mlsanity.com/paper/2502.05589/) (2025)
- [Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR](https://mlsanity.com/paper/2508.14029/) (2025)
- [Chain-of-Retrieval Augmented Generation](https://mlsanity.com/paper/2501.14342/) (2025)
- [A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2511.17208/) (2025)
- [Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents](https://mlsanity.com/paper/2505.19997/) (2025)
- [Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogue](https://mlsanity.com/paper/2509.10852/) (2025)
- [Semantic Alignment for Multimodal Large Language Models](https://mlsanity.com/paper/2408.12867/) (2024)
- [ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generation](https://mlsanity.com/paper/2402.12408/) (2024)
- [Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction](https://mlsanity.com/paper/2508.11184/) (2025)

## Built on by (most cited first, 8 of 8)

- [Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory](https://mlsanity.com/paper/2605.10870/) (2026)
- [Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval](https://mlsanity.com/paper/2605.11325/) (2026)
- [Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering](https://mlsanity.com/paper/2608.27925/) (2026)
- [SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue](https://mlsanity.com/paper/2609.26780/) (2026)
- [EMIR2: Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval](https://mlsanity.com/paper/2609.32584/) (2026)
- [Contract Memory Compiler: Resolve, Then Traverse](https://mlsanity.com/paper/2609.32658/) (2026)
- [Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory](https://mlsanity.com/paper/2609.33822/) (2026)
- [Stashbird: Efficient Speaker-Indexed Memory for Conversational Agents](https://mlsanity.com/paper/2609.34242/) (2026)

## Abstract (arXiv)

AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini.