mlsanityData to 7 Oct 2026

eMEM: A Hybrid Spatio-Temporal Memory System For Embodied Agents

arXiv 2606.03374 ↗First posted 2 Jun 2026cs.ROcited by 1

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments. Current agent memory architectures, such as Generative Agents, MemGPT, and A-MEM, treat memory as text streams or knowledge graphs, but embodied agents require memory that is simultaneously searchable by meaning, space, and time. eMEM fills this gap with a multi-index architecture (SQLITE for structured storage, hnswlib for approximate nearest neighbour semantic search, and an R-tree for spatial queries) unified behind a single graph model. A tiered consolidation pipeline transforms raw perceptual observations into compressed summaries, mirroring hippocampal-neocortical consolidation in biological systems. Ten agent-facing recall tools expose memory retrieval primitives, including concept-to-location resolution and cross layer recall, as first-class operations for LLM tool calling. The system is fully embedded and runs in-process alongside the agent. In addition we introduce eMEM-Bench v1, a benchmark we construct over ProcTHOR-10K scenes for embodied memory evaluation. The benchmark is organised explicitly around eight cognitive-psychology paradigms (DRM lures, pattern separation, pattern completion, source monitoring, context-dependent retrieval, long-horizon interference, serial position, and a foil augmented retention curve), each chosen so that the result is interpretable against the broader memory-systems literature in humans and prior agent-memory systems; a level of diagnostic that surface-task benchmarks like LoCoMo or OpenEQA cannot provide. eMEM scores 80.8 weighted mean over 988 probes, with a flat retention curve at ceiling from 1 h to 1 yr of simulated delay on room-unique items. We show that a pure RAG baseline (the flat_rag ablation) loses 30 pt on context dependent retrieval and 29 pt on DRM lure rejection, isolating the contribution of multi-layer storage and consolidation respectively. We release both the system and the benchmark code.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 22 of its 51 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

22 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025FindingDory: A Benchmark to Evaluate Memory in Embodied Agents18 Jun

Other references · 21

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  5. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  6. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  7. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  8. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  9. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  10. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  11. 2022Visual Language Maps for Robot Navigationcited by 362
  12. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 357
9 more
  1. 2022SQA3D: Situated Question Answering in 3D Scenescited by 303
  2. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 289
  3. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  4. 2022Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimizationcited by 175
  5. 2025Training Sparse Mixture Of Experts Text Embedding Modelscited by 32
  6. 2024EmbodiedRAG: Dynamic 3D Scene Graph Retrieval for Efficient and Scalable Robot Task Planningcited by 23
  7. 2026Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Explorationcited by 13
  8. 2022A Memory System of a Robot Cognitive Architecture and its Implementation in ArmarXcited by 11
  9. 2025Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directionscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks
  2. 2026EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents
  3. 2025Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
  4. 2024Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
  5. 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
  6. 2025RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
  7. 2026Analytic Concept-Centric Memory for Agentic Embodied Manipulation
  8. 2026Hippocampus: An Efficient and Scalable Memory Module for Agentic AI