CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
On the map: LLM agents and tool use → Reinforcement learning for LLM agents
Abstract (arXiv)
Developing general-purpose embodied agents is a core challenge in AI. Minecraft provides rich complexity and internet-scale data, but its slow speed and engineering overhead make it unsuitable for rapid prototyping. Crafter offers a lightweight alternative that retains key challenges from Minecraft, yet its use has remained limited to narrow tasks due to the absence of foundation models that have driven progress in the Minecraft setting. In this paper, we present CrafterDojo, a suite of foundation models and tools that unlock the Crafter environment as a lightweight, prototyping-friendly, and Minecraft-like testbed for general-purpose embodied agent research. CrafterDojo addresses this by introducing CrafterVPT, CrafterCLIP, and CrafterSteve-1 for behavior priors, vision-language grounding, and instruction following, respectively. In addition, we provide toolkits for generating behavior and caption datasets (CrafterPlay and CrafterCaption), reference agent implementations, benchmark evaluations, and a complete open-source codebase.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 19 of its 23 references that are in the map. First posted on arXiv 19 Aug 2025.
Builds on
19 of 23 references.
Closest ancestors · 5
Same direction, newest first
- 2024MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory11 Nov
- 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks7 Aug
- 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models10 Nov
- 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling28 Jan
- 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge17 Jun
Other references · 14
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
- 2023Mastering Diverse Domains through World Modelscited by 1,193
- 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 645
- 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
- 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
- 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraftcited by 95
- 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 80
- 2023MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perceptioncited by 67
- 2024Efficient World Models with Context-Aware Tokenizationcited by 33
- 2025Improving Transformer World Models for Data-Efficient RLcited by 13
2 more
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
- 2025OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
- 2023See and Think: Embodied Agent in Virtual Environment
- 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
- 2025Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
- 2024Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification
- 2024APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents
- 2026MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft