mlsanityData to 7 Oct 2026

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

arXiv 2601.02845 ↗First posted 6 Jan 2026cs.CL cs.AIcited by 26

On the map: LLM agents and tool use → Agent memory systems

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.

Key facts. Cited by 26 papers in the map (data through 7 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.

Builds on

26 of 34 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents23 Dec
  2. 2025ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents17 Nov
  3. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning3 Nov
  4. 2025Preference-Aware Memory Update for Long-Term LLM Agents10 Oct
  5. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agents5 Aug
  6. 2025Memory OS of AI Agent30 May
  7. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  8. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents11 Mar
  9. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  10. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  11. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Management16 Jun
  12. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 14

  1. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  3. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  4. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  5. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  6. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  7. 2023LongLoRA: Efficient Fine-tuning of Long-Context Large Language Modelscited by 243
  8. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  9. 2024Personalization of Large Language Models: A Surveycited by 100
  10. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 77
  11. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 68
  12. 2024HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processingcited by 20
2 more
  1. 2025Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMscited by 18
  2. 2025MemLoRA: Distilling Expert Adapters for On-Device Memory Systemscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 26.

26 papers.

Sort:

By area:

  1. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 9
  2. 2026Adaptive Information Control for Search-Augmented LLM Reasoningcited by 8
  3. 2026Self-GC: Self-Governing Context for Long-Horizon LLM Agentscited by 8
  4. 2026Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agentscited by 6
  5. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  6. 2026Hierarchical Memory Orchestration for Personalized Persistent Agentscited by 3
  7. 2026LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memorycited by 3
  8. 2026LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidationcited by 3
  9. 2026TraceMem: Weaving Narrative Memory Schemata from User Conversational Tracescited by 2
  10. 2026ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Contextcited by 2
  11. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memorycited by 2
  12. 2026MemPro: Agentic Memory Systems as Evolvable Programscited by 2
14 more
  1. 2026PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agentscited by 2
  2. 2026Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agentscited by 1
  3. 2026SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agentscited by 1
  4. 2026MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrievalcited by 1
  5. 2026Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMocited by 0
  6. 2026Stateless Decision Memory for Enterprise AI Agentscited by 0
  7. 2026Recall Isn't Enough: Bounding Commitments in Personalized Language Systemscited by 0
  8. 2026Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baselinecited by 0
  9. 2026MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scalecited by 0
  10. 2026Entity-Memory Graph Retrieval Improves Evidence Coverage in Long-Conversation Question Answeringcited by 0
  11. 2026AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memorycited by 0
  12. 2026EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systemscited by 0
  13. 2026MemCalib: Benchmarking and Optimizing Memory Use in LLM Agentscited by 0
  14. 2026The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
  2. 2026Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
  3. 2026Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents
  4. 2026MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
  5. 2025A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents
  6. 2026ArborMem: Navigating Interaction States with Memory Forests
  7. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
  8. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents