# TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

arXiv: https://arxiv.org/abs/2601.02845 · HTML: https://mlsanity.com/paper/2601.02845/

## Key facts

- Cited by 31 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 26 of its 34 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [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)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs](https://mlsanity.com/paper/2410.14052/) (2024)
- [MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models](https://mlsanity.com/paper/2505.22101/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [What Deserves Memory: Adaptive Memory Distillation for LLM Agents](https://mlsanity.com/paper/2508.03341/) (2025)
- [LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning](https://mlsanity.com/paper/2511.01448/) (2025)
- [HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing](https://mlsanity.com/paper/2405.06067/) (2024)
- [Preference-Aware Memory Update for Long-Term LLM Agents](https://mlsanity.com/paper/2510.09720/) (2025)
- [Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs](https://mlsanity.com/paper/2512.03324/) (2025)
- [MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents](https://mlsanity.com/paper/2512.20237/) (2025)
- [ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents](https://mlsanity.com/paper/2511.12960/) (2025)
- [MemLoRA: Distilling Expert Adapters for On-Device Memory Systems](https://mlsanity.com/paper/2512.04763/) (2025)

## Built on by (most cited first, 30 of 31)

- [StructMem: Structured Memory for Long-Horizon Behavior in LLMs](https://mlsanity.com/paper/2604.21748/) (2026)
- [MemSyco-Bench: Benchmarking Sycophancy in Agent Memory](https://mlsanity.com/paper/2607.01071/) (2026)
- [Adaptive Information Control for Search-Augmented LLM Reasoning](https://mlsanity.com/paper/2602.01672/) (2026)
- [Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents](https://mlsanity.com/paper/2606.06090/) (2026)
- [Self-GC: Self-Governing Context for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.00692/) (2026)
- [LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2607.22690/) (2026)
- [Hierarchical Memory Orchestration for Personalized Persistent Agents](https://mlsanity.com/paper/2604.01670/) (2026)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context](https://mlsanity.com/paper/2604.01599/) (2026)
- [MemPro: Agentic Memory Systems as Evolvable Programs](https://mlsanity.com/paper/2606.00619/) (2026)
- [LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation](https://mlsanity.com/paper/2608.12990/) (2026)
- [TraceMem: Weaving Narrative Memory Schemata from User Conversational Traces](https://mlsanity.com/paper/2602.09712/) (2026)
- [SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory](https://mlsanity.com/paper/2605.12061/) (2026)
- [PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents](https://mlsanity.com/paper/2606.04780/) (2026)
- [Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents](https://mlsanity.com/paper/2604.19457/) (2026)
- [Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline](https://mlsanity.com/paper/2606.04315/) (2026)
- [SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents](https://mlsanity.com/paper/2608.08055/) (2026)
- [MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval](https://mlsanity.com/paper/2609.03201/) (2026)
- [MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents](https://mlsanity.com/paper/2609.24259/) (2026)
- [Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo](https://mlsanity.com/paper/2604.11563/) (2026)
- [Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation](https://mlsanity.com/paper/2604.11628/) (2026)
- [Stateless Decision Memory for Enterprise AI Agents](https://mlsanity.com/paper/2604.20158/) (2026)
- [Recall Isn't Enough: Bounding Commitments in Personalized Language Systems](https://mlsanity.com/paper/2605.16712/) (2026)
- [MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale](https://mlsanity.com/paper/2608.02613/) (2026)
- [Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answering](https://mlsanity.com/paper/2608.27925/) (2026)
- [AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory](https://mlsanity.com/paper/2609.21940/) (2026)
- [EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems](https://mlsanity.com/paper/2609.22231/) (2026)
- [The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents](https://mlsanity.com/paper/2609.33013/) (2026)
- [AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory](https://mlsanity.com/paper/2610.07707/) (2026)
- [Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval](https://mlsanity.com/paper/2610.08300/) (2026)

## Abstract (arXiv)

Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, often leading to fragmented memories and unstable long-horizon personalization. We present TiMem, a temporal--hierarchical memory framework that organizes conversations through a Temporal Memory Tree (TMT), enabling systematic memory consolidation from raw conversational observations to progressively abstracted persona representations. TiMem is characterized by three core properties: (1) temporal--hierarchical organization through TMT; (2) semantic-guided consolidation that enables memory integration across hierarchical levels without fine-tuning; and (3) complexity-aware memory recall that balances precision and efficiency across queries of varying complexity. Under a consistent evaluation setup, TiMem achieves state-of-the-art accuracy on both benchmarks, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S. It outperforms all evaluated baselines while reducing the recalled memory length by 52.20% on LoCoMo. Manifold analysis indicates clear persona separation on LoCoMo and reduced dispersion on LongMemEval-S. Overall, TiMem treats temporal continuity as a first-class organizing principle for long-horizon memory in conversational agents. The code is available at https://github.com/TiMEM-AI/timem.