# RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

arXiv: https://arxiv.org/abs/2506.06677 · HTML: https://mlsanity.com/paper/2506.06677/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 7 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 24 of 24)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2412.18194/) (2024)
- [CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models](https://mlsanity.com/paper/2403.08248/) (2024)
- [Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy](https://mlsanity.com/paper/2503.19757/) (2025)
- [ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes](https://mlsanity.com/paper/2304.04321/) (2023)
- [VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation](https://mlsanity.com/paper/2206.08522/) (2022)
- [VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection](https://mlsanity.com/paper/2411.14794/) (2024)
- [BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation](https://mlsanity.com/paper/2410.06237/) (2024)
- [When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding](https://mlsanity.com/paper/2506.05551/) (2025)
- [LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions](https://mlsanity.com/paper/2311.11904/) (2023)

## Built on by (most cited first, 30 of 34)

- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design](https://mlsanity.com/paper/2603.01229/) (2026)
- [Vision Language Action Models in Robotic Manipulation: A Systematic Review](https://mlsanity.com/paper/2507.10672/) (2025)
- [LIBERO-X: Robustness Litmus for Vision-Language-Action Models](https://mlsanity.com/paper/2602.06556/) (2026)
- [EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies](https://mlsanity.com/paper/2606.20092/) (2026)
- [PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.07060/) (2026)
- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation](https://mlsanity.com/paper/2509.19524/) (2025)
- [μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models](https://mlsanity.com/paper/2606.12497/) (2026)
- [H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model](https://mlsanity.com/paper/2602.11291/) (2026)
- [vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models](https://mlsanity.com/paper/2603.13966/) (2026)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents](https://mlsanity.com/paper/2605.24598/) (2026)
- [Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation](https://mlsanity.com/paper/2607.05377/) (2026)
- [Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models](https://mlsanity.com/paper/2605.29074/) (2026)
- [ManiAgent: An Agentic Framework for General Robotic Manipulation](https://mlsanity.com/paper/2510.11660/) (2025)
- [RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks](https://mlsanity.com/paper/2510.14968/) (2025)
- [TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning](https://mlsanity.com/paper/2605.07943/) (2026)
- [WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation](https://mlsanity.com/paper/2606.26443/) (2026)
- [MobileManiBench: Simplifying Model Verification for Mobile Manipulation](https://mlsanity.com/paper/2602.05233/) (2026)
- [DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?](https://mlsanity.com/paper/2606.12402/) (2026)
- [SparkVLA: Stop-Aware Hierarchical VLA with Adaptive Action Chunking for Long-Horizon Manipulation](https://mlsanity.com/paper/2608.16172/) (2026)
- [Behavior-Skill: A Fine-Grained Benchmark for Evaluating Vision-Language-Action Policies in Long-Horizon Tasks](https://mlsanity.com/paper/2608.30536/) (2026)
- [StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation](https://mlsanity.com/paper/2609.20791/) (2026)
- [GenPlanner: From Noise to Plans -- Emergent Reasoning in Flow Matching and Diffusion Models](https://mlsanity.com/paper/2602.18812/) (2026)
- [Reference-Free Assessment of Physical Consistency in World Model-based Video Generation](https://mlsanity.com/paper/2606.22363/) (2026)
- [Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities](https://mlsanity.com/paper/2608.08045/) (2026)
- [Benchmarking World Models for Continual Learning on Compositional Tasks](https://mlsanity.com/paper/2609.22055/) (2026)
- [RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models](https://mlsanity.com/paper/2609.34384/) (2026)

## Abstract (arXiv)

Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive System 1 policies, underutilizing VLMs' strengths in semantic reasoning and long-horizon planning. These System 2 capabilities-characterized by deliberative, goal-directed thinking-remain under explored due to the limited temporal scale and structural complexity of current benchmarks. To address this gap, we introduce RoboCerebra, a benchmark for evaluating high-level reasoning in long-horizon robotic manipulation. RoboCerebra includes: (1) a large-scale simulation dataset with extended task horizons and diverse subtask sequences in household environments; (2) a hierarchical framework combining a high-level VLM planner with a low-level vision-language-action (VLA) controller; and (3) an evaluation protocol targeting planning, reflection, and memory through structured System 1-System 2 interaction. The dataset is constructed via a top-down pipeline, where GPT generates task instructions and decomposes them into subtask sequences. Human operators execute the subtasks in simulation, yielding high-quality trajectories with dynamic object variations. Compared to prior benchmarks, RoboCerebra features significantly longer action sequences and denser annotations. We further benchmark state-of-the-art VLMs as System 2 modules and analyze their performance across key cognitive dimensions, advancing the development of more capable and generalizable robotic planners.