# Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy

arXiv: https://arxiv.org/abs/2502.19902 · HTML: https://mlsanity.com/paper/2502.19902/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 14 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [STEVE-1: A Generative Model for Text-to-Behavior in Minecraft](https://mlsanity.com/paper/2306.00937/) (2023)
- [Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks](https://mlsanity.com/paper/2408.03615/) (2024)
- [MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception](https://mlsanity.com/paper/2312.07472/) (2023)
- [Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft](https://mlsanity.com/paper/2312.09238/) (2023)
- [GROOT: Learning to Follow Instructions by Watching Gameplay Videos](https://mlsanity.com/paper/2310.08235/) (2023)
- [Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction](https://mlsanity.com/paper/2301.10034/) (2023)
- [OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents](https://mlsanity.com/paper/2407.00114/) (2024)

## Built on by (most cited first, 25 of 25)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](https://mlsanity.com/paper/2503.03663/) (2025)
- [GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent](https://mlsanity.com/paper/2505.16827/) (2025)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation](https://mlsanity.com/paper/2511.10518/) (2025)
- [Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills](https://mlsanity.com/paper/2506.10387/) (2025)
- [STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization](https://mlsanity.com/paper/2506.03863/) (2025)
- [HiconAgent: History Context-aware Policy Optimization for GUI Agents](https://mlsanity.com/paper/2512.01763/) (2025)
- [SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds](https://mlsanity.com/paper/2512.01078/) (2025)
- [PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning](https://mlsanity.com/paper/2507.08064/) (2025)
- [ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2605.05126/) (2026)
- [From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model](https://mlsanity.com/paper/2605.22671/) (2026)
- [DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts](https://mlsanity.com/paper/2508.07842/) (2025)
- [NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning](https://mlsanity.com/paper/2510.19429/) (2025)
- [Experience Transfer for Multimodal LLM Agents in Minecraft Game](https://mlsanity.com/paper/2604.05533/) (2026)
- [MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents](https://mlsanity.com/paper/2505.20148/) (2025)
- [GuessBench: Sensemaking Multimodal Creativity in the Wild](https://mlsanity.com/paper/2506.00814/) (2025)
- [MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents](https://mlsanity.com/paper/2603.13131/) (2026)
- [ASH: Agents that Self-Hone in Long-Horizon Worlds](https://mlsanity.com/paper/2605.14211/) (2026)
- [Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration](https://mlsanity.com/paper/2606.00145/) (2026)
- [Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents](https://mlsanity.com/paper/2606.13097/) (2026)
- [SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning](https://mlsanity.com/paper/2606.29932/) (2026)
- [OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation](https://mlsanity.com/paper/2609.39727/) (2026)
- [MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents](https://mlsanity.com/paper/2610.13829/) (2026)

## Abstract (arXiv)

Building an agent that can mimic human behavior patterns to accomplish various open-world tasks is a long-term goal. To enable agents to effectively learn behavioral patterns across diverse tasks, a key challenge lies in modeling the intricate relationships among observations, actions, and language. To this end, we propose Optimus-2, a novel Minecraft agent that incorporates a Multimodal Large Language Model (MLLM) for high-level planning, alongside a Goal-Observation-Action Conditioned Policy (GOAP) for low-level control. GOAP contains (1) an Action-guided Behavior Encoder that models causal relationships between observations and actions at each timestep, then dynamically interacts with the historical observation-action sequence, consolidating it into fixed-length behavior tokens, and (2) an MLLM that aligns behavior tokens with open-ended language instructions to predict actions auto-regressively. Moreover, we introduce a high-quality Minecraft Goal-Observation-Action (MGOA)} dataset, which contains 25,000 videos across 8 atomic tasks, providing about 30M goal-observation-action pairs. The automated construction method, along with the MGOA dataset, can contribute to the community's efforts to train Minecraft agents. Extensive experimental results demonstrate that Optimus-2 exhibits superior performance across atomic tasks, long-horizon tasks, and open-ended instruction tasks in Minecraft. Please see the project page at https://cybertronagent.github.io/Optimus-2.github.io/.