Skip to content
Preprint

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Sep 2026 · 1 citation · 43 references
Computer Science

TL;DR

Under matched backbones, EMem achieves the best overall performance among the evaluated memory systems and improves both open-source and proprietary models, while EMem-8B further improves over its backbone.

Abstract

Long-horizon embodied interaction requires agents to retain and continually update information about the environment as they observe, act, and encounter change. Yet current agents struggle to maintain such memory reliably. Our analysis traces this limitation to four key deficiencies: weak fine-grained visual memory, unreliable dynamic world-state tracking, failing to record world state revealed by interaction outcomes, and limited generalization from prior experience. However, existing benchmarks do not directly assess these memory capabilities during long-horizon embodied interaction. To address this gap, we introduce EmbodiedMemory-Bench (EMem-Bench), comprising 2,554 interactive episodes across four task families. EMem-Bench requires agents to build and update memory from interaction history, then use it to complete a later task by acting in the environment. We further present Embodied-Memorizer (EMem), an external memory system that organizes embodied experience into spatial, event, and scene memories. We also train EMem-8B, an 8B policy that manages and uses these memories. We evaluate a diverse range of open-source and proprietary MLLMs and representative multimodal memory systems. Results show that current models remain weak and uneven across the four challenges. Under matched backbones, EMem achieves the best overall performance among the evaluated memory systems and improves both open-source and proprietary models, while EMem-8B further improves over its backbone. Project page: https://zju-omniai.github.io/EmbodiedMemoryBench/

View source

Similar papers

#artificial intelligence Review Oct 2026

When the Past Shapes Action: Understanding Embodied Memory

This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation, and provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.

Si-Qi Li, Zi-Yi Bai, Xinrun Xu et al. · 0 citations
Preprint Oct 2026

What Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied Agents

Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks an...

Jun-Xiang Wang, Yu-Chen Liu, Yi Wu et al. · 0 citations
Preprint Sep 2026

ME-Brain-1.0: Memory, Cognition and Action for Evolving Embodied Intelligence

MachEmbodied-Brain (ME-Brain) is introduced, a self-evolving embodied system organized around a closed loop of action execution, experience acquisition, experience evolution, and improved execution that shifts embodied intelligence from train-and-freeze to deploy-and-evolve without model retraining.

Wei He, Heng-Tao Li, Chen-Feng Wang et al. · 2 citations
Preprint Oct 2026

Mem4Act: Learning Effective Latent Memory for Long-Horizon Robotic Manipulation

Long-horizon robotic manipulation fundamentally requires memory: agents must retain task-relevant information from past observations and interactions and use it to guide future actions. Existing approaches typically preserve raw historical observations, compressed visual tokens, or language summaries, but these represe...

Yun Zhang, Zhi-Yu Huang, Tian-Hui Cai et al. · 1 citation
Preprint Oct 2026

ReSight: Task-Driven Self-Improving Memory for Embodied Agents

Robots can use historical observations to answer spatiotemporal queries in familiar environments, but the presence of relevant evidence does not imply that existing tools support the operations a task requires. We introduce ReSight, a task-driven self-improving memory system for embodied agents that expands the capabil...

Li-Rong Che, Yang Chen, Yi-Meng Su et al. · 2 citations · ⚡1
Preprint Oct 2026

MemVLN: Streaming Episodic Memory for Vision-Language Navigation

Vision-language navigation (VLN) requires an embodied agent to follow language instructions through 3D environments. Maintaining persistent episodic memory remains a challenge for VLM-based streaming agents in long-horizon navigation. We present MEMVLN, a streaming episodic memory framework that maintains a bounded ban...

Yan Wang, Jiangyong Huang, Si-Yuan Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.