# RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

arXiv: https://arxiv.org/abs/2605.10921 · HTML: https://mlsanity.com/paper/2605.10921/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2026.

## Built on by (most cited first, 22 of 22)

- [EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies](https://mlsanity.com/paper/2606.20092/) (2026)
- [MemoryWAM: Efficient World Action Modeling with Persistent Memory](https://mlsanity.com/paper/2606.20562/) (2026)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [HarnessWAM: Bridging Prediction and Deliberation in World Action Models](https://mlsanity.com/paper/2608.09516/) (2026)
- [Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory](https://mlsanity.com/paper/2608.16889/) (2026)
- [SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models](https://mlsanity.com/paper/2609.05533/) (2026)
- [2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation](https://mlsanity.com/paper/2609.11308/) (2026)
- [MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation](https://mlsanity.com/paper/2609.07047/) (2026)
- [TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces](https://mlsanity.com/paper/2609.20646/) (2026)
- [RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents](https://mlsanity.com/paper/2609.32862/) (2026)
- [RoboMME-Interference: Benchmarking Robot Memory Under Interference](https://mlsanity.com/paper/2606.22338/) (2026)
- [Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation](https://mlsanity.com/paper/2608.09410/) (2026)
- [StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.22684/) (2026)
- [ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation](https://mlsanity.com/paper/2609.24124/) (2026)
- [EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks](https://mlsanity.com/paper/2609.28236/) (2026)
- [RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models](https://mlsanity.com/paper/2609.34384/) (2026)
- [Simple Agentic Memory for Generalist Robot Policies](https://mlsanity.com/paper/2609.36595/) (2026)
- [Remember What You Did: Action-History Memory with Dual-Expert Denoising for Long-Horizon Vision-Language-Action Policies](https://mlsanity.com/paper/2609.37307/) (2026)
- [LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation](https://mlsanity.com/paper/2609.39507/) (2026)
- [Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts](https://mlsanity.com/paper/2609.39526/) (2026)
- [EMBER-Bench: Benchmarking Cross-Event Causal Memory in Long-Horizon Embodied Tasks](https://mlsanity.com/paper/2610.05013/) (2026)
- [PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning](https://mlsanity.com/paper/2610.11168/) (2026)

## Abstract (arXiv)

Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments. However, existing robotic memory benchmarks still lack multimodal annotations for memory formation, provide limited task coverage and structural complexity, and remain restricted to simulation without real-world evaluation. We address this gap with RoboMemArena, a large-scale benchmark of 26 tasks, with average trajectory lengths exceeding 1,000 steps per task and 68.9% of subtasks being memory-dependent. The generation pipeline leverages a vision-language model (VLM) to design and compose subtasks, generates full trajectories through atomic functions, and provides memory-related annotations, including subtask instructions and native keyframe annotations, while paired real-world memory tasks support physical evaluation. We further design PrediMem, a dual-system VLA in which a high-level VLM planner manages a memory bank with recent and keyframe buffers and uses a predictive coding head to improve sensitivity to task dynamics. Extensive experiments on RoboMemArena show that PrediMem outperforms all baselines and provides insights into memory management, model architecture, and scaling laws for complex memory systems.