mlsanityData to 14 Oct 2026

STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning

arXiv 2502.10177 ↗First posted 14 Feb 2025cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

A key objective of embodied intelligence is enabling agents to perform long-horizon tasks in dynamic environments while maintaining robust decision-making and adaptability. To achieve this goal, we propose the Spatio-Temporal Memory Agent (STMA), a novel framework designed to enhance task planning and execution by integrating spatio-temporal memory. STMA is built upon three critical components: (1) a spatio-temporal memory module that captures historical and environmental changes in real time, (2) a dynamic knowledge graph that facilitates adaptive spatial reasoning, and (3) a planner-critic mechanism that iteratively refines task strategies. We evaluate STMA in the TextWorld environment on 32 tasks, involving multi-step planning and exploration under varying levels of complexity. Experimental results demonstrate that STMA achieves a 31.25% improvement in success rate and a 24.7% increase in average score compared to the state-of-the-art model. The results highlight the effectiveness of spatio-temporal memory in advancing the memory capabilities of embodied agents.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 71 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

30 of 71 references.

References · 30

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  8. 2016Progressive Neural Networkscited by 1,361
  9. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  10. 2022A Generalist Agentcited by 808
  11. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  12. 2019Model-Based Reinforcement Learning for Ataricited by 502
18 more
  1. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 319
  2. 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
  3. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  4. 2018Distributed Prioritized Experience Replaycited by 269
  5. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 265
  6. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  7. 2023AdaPlanner: Adaptive Planning from Feedback with Language Modelscited by 196
  8. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  9. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
  10. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 153
  11. 2018Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applicationscited by 127
  12. 2023A Tutorial on Meta-Reinforcement Learningcited by 108
  13. 2019Scene Memory Transformer for Embodied Agents in Long-Horizon Taskscited by 107
  14. 2017Neural Map: Structured Memory for Deep Reinforcement Learningcited by 90
  15. 2023LLM-Rec: Personalized Recommendation via Prompting Large Language Modelscited by 77
  16. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  17. 2023LARP: Language-Agent Role Play for Open-World Gamescited by 24
  18. 2020Deep Reinforcement Learning (DRL): Another Perspective for Unsupervised Wireless Localizationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Neural Brain: A Neuroscience-inspired Framework for Embodied Agentscited by 10
  2. 2026MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon taskscited by 8
  3. 2026BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planningcited by 2
  4. 2025AMAP Agentic Planning Technical Reportcited by 1
  5. 2026Mosaic: Runtime-Efficient Multi-Agent Embodied Planningcited by 1
  6. 2026MIND: Instruction-Conditioned Incremental Grounding for Robotscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems
  2. 2026LASAR: Towards Spatio-temporal Reasoning with Latent Cognitive Map
  3. 2026Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
  4. 2024KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
  5. 2025FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
  6. 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
  7. 2026RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy
  8. 2025EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer