# Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents

arXiv: https://arxiv.org/abs/2601.03785 · HTML: https://mlsanity.com/paper/2601.03785/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

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

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [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)
- [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)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://mlsanity.com/paper/2306.04136/) (2023)
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022)
- [SCM: Enhancing Large Language Model with Self-Controlled Memory Framework](https://mlsanity.com/paper/2304.13343/) (2023)
- [ConveRT: Efficient and Accurate Conversational Representations from Transformers](https://mlsanity.com/paper/1911.03688/) (2019)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](https://mlsanity.com/paper/1902.04793/) (2019)
- [DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents](https://mlsanity.com/paper/2406.13144/) (2024)
- [Knowledge Graph-extended Retrieval Augmented Generation for Question Answering](https://mlsanity.com/paper/2504.08893/) (2025)
- [SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation](https://mlsanity.com/paper/2305.08371/) (2023)
- [Guided Navigation in Knowledge-Dense Environments: Structured Semantic Exploration with Guidance Graphs](https://mlsanity.com/paper/2508.10012/) (2025)

## Built on by (most cited first, 6 of 6)

- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [Query-focused and Memory-aware Reranker for Long Context Processing](https://mlsanity.com/paper/2602.12192/) (2026)
- [SwiftMem: Fast Agentic Memory via Query-aware Indexing](https://mlsanity.com/paper/2601.08160/) (2026)
- [GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory](https://mlsanity.com/paper/2605.01688/) (2026)
- [MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents](https://mlsanity.com/paper/2607.24097/) (2026)
- [EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems](https://mlsanity.com/paper/2609.22231/) (2026)

## Abstract (arXiv)

Long-term human-agent dialogues are organized by topic continuity: adjacent turns often develop the same goal, plan, problem, or event, while related activities may recur across distant sessions. Yet many LLM agent memory systems first decompose histories into isolated turns or fixed-size chunks, then compensate through enrichment, consolidation, or retrieval mechanisms still tied to semantic proximity or fragment-level records. This weakens temporal and causal organization and biases memory access toward semantic proximity rather than task- or topic-level continuity. We introduce Membox, a hierarchical memory architecture that instantiates topic continuity as an explicit organization layer for agent memory. Its Topic Loom incrementally organizes dialogue streams into boxes whose internal turns follow the same local topic, while its Trace Weaver links extracted events across boxes into macro-topic traces that recover recurring activities, goals, and factual developments across distant sessions. On LoCoMo, Topic-Loom-only retrieval improves over the best Mem0/A-MEM retrieval-depth setting by 13.00 F1 points (53.95 vs. 40.95), and trace-expanded retrieval further raises F1 to 55.28; with GPT-4o, trace-expanded retrieval reaches 59.71 F1. Additional DialSim results show the same gain from adding cross-box traces in multi-party dialogue. These results show that local topic-continuity organization and macro-topic trace expansion improve long-range memory beyond semantic retrieval over fragmented records.