--- title: "STEVE-1 | Minecraft Instruction-Following Agent | world-models.io" canonical: "https://world-models.io/en/models/steve-1/" description: "STEVE-1 is an instruction-following agent for Minecraft that uses a generative world model for open-ended gameplay." author: "Tyler D." generated: "2026-10-30" --- New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time. The Knowledge Hub for AI World Models # STEVE-1 STEVE-1 is a generative agent for Minecraft that follows text and visual instructions, using a latent world model to navigate and interact in open-ended 3D environments. robotics model-based-rl simulation embodied-ai ## What is a world model? A world model is an AI system that learns a predictive representation of how an environment changes over time. It can use observations, actions, or language to estimate future states and possible outcomes before an agent acts. World models support planning in model-based reinforcement learning, robotics, embodied AI, autonomous driving, and interactive simulation. This site catalogs these systems with model records, research papers, benchmark context, and source links. Start with the [world models database](https://world-models.io/en/world-models-database/), compare systems on the [leaderboard](https://world-models.io/en/leaderboard/), or read the [Performance Index methodology](https://world-models.io/en/methodology/performance-index/). ## Key Attributes Static HTML snapshot of the model record for crawlers and no-JS readers. | Attribute | Value | | --- | --- | | Model | STEVE-1 | | Lab / Organization | UT Austin | | Category | Generative World Model | | Subtype | Instruction-Following Game Agent | | World Model Type | Text-conditioned generative agent in open-world | | Primary Domain | Game AI / Open World | | Architecture | VPT backbone + MineCLIP goal encoder + latent-conditioned policy | | Modality | Visual + Language (instructions) | | Training Method | Hindsight relabeling on unlabeled gameplay + CLIP-based instruction conditioning | | Status | active | | Year | 2023 | | Performance Index | 53/100 (medium confidence, v1.1) | ## About STEVE-1 Main editorial body preserved directly in static HTML. STEVE-1 is a generative agent for Minecraft that follows open-ended text and visual instructions. Built on top of a VPT (Video Pre-Training) backbone, STEVE-1 uses a latent-conditioned policy that translates CLIP-based goal embeddings into action sequences. It demonstrates that combining large-scale video pre-training with instruction-conditioned generation creates agents capable of executing diverse, compositional tasks in open-world environments. STEVE-1 is a text-conditioned generative agent in open-world developed by UT Austin in 2023 for game ai / open world. ## Editorial Snapshot Short extractable facts for answer engines and no-JS readers. | Signal | Value | | --- | --- | | Definition | STEVE-1 is a text-conditioned generative agent in open-world developed by UT Austin in 2023 for game ai / open world. | | Short Description | An instruction-following agent for Minecraft that uses a generative world model to execute open-ended text commands. | | Benchmark Rows | 1 | | FAQ Entries | 2 | | Related Models | 4 | | Related Guides | 0 | | Related Research Topics | 0 | | Last Updated | 2026-04-07 | ## Notable Features Key capabilities associated with this model. - • Open-ended instruction following - • Minecraft open-world navigation - • CLIP-based goal conditioning - • No reward function needed ## Use Cases Representative applications attached to this model record. Open-world game playing Instruction-following agents Creative task execution Embodied language grounding ## Strengths and Limitations Balanced assessment surfaced in static HTML. ### Strengths - • Handles diverse open-ended instructions - • No reward engineering needed - • Scales with video pre-training data - • Compositional task understanding ### Limitations - • Minecraft-specific - • Limited long-horizon planning - • Requires large pre-training corpus - • Short action horizons ## Benchmarks Published benchmark evidence attached to this model record. | Benchmark | Metric | Result | Source | | --- | --- | --- | --- | | Programmatic Eval | Task Completion | Strong instruction-following | [Source](https://arxiv.org/abs/2306.00937) | ## References and Citations Primary references preserved in static HTML for citation extraction. | Reference | Link | | --- | --- | | Lifshitz et al., 2023. STEVE-1: A Generative Model for Text-to-Behavior in Minecraft. arXiv:2306.00937 | [Open source](https://arxiv.org/abs/2306.00937) | ## Related Models Nearby models linked from the current editorial record. | Model | Category | World Model Type | Index v1.1 | | --- | --- | --- | --- | | [DreamerV3](https://world-models.io/en/models/dreamer-v3/) | Model-Based RL | Imagination-based dynamics model | 88/100 | | [Genie](https://world-models.io/en/models/genie-1/) | Generative World Model | Action-controllable generative model | 57/100 | | [OASIS](https://world-models.io/en/models/oasis/) | Generative World Model | Real-time playable world model | 66/100 | | [GameNGen](https://world-models.io/en/models/gamengen/) | Generative World Model | Diffusion-based neural game engine | 52/100 | ## Direct Comparisons Side-by-side comparisons already connected to this model. | Comparison | Matchup | Summary | | --- | --- | --- | | [STEVE-1 vs DreamerV3](https://world-models.io/en/compare/steve-1-vs-dreamer-v3/) | STEVE-1 vs DreamerV3 | Two approaches to open-world game AI. STEVE-1 uses video pre-training and instruction following, while DreamerV3 learns a world model from scratch via reinforcement learning. | ## Frequently Asked Questions FAQ answers rendered directly into static HTML for extractable responses. ### How is STEVE-1 different from DreamerV3 in Minecraft? DreamerV3 learns from scratch via RL and a world model. STEVE-1 uses large-scale video pre-training (VPT) and instruction conditioning, requiring no reward function but needing more pre-training data. ### Can STEVE-1 be applied outside Minecraft? The architecture is Minecraft-specific, but the approach of combining video pre-training with instruction conditioning is applicable to any visual domain with abundant video data. ## Quick Answer Short extractable summary preserved directly in static HTML. - STEVE-1 is a text-conditioned generative agent in open-world developed by UT Austin in 2023 for game ai / open world. - Use this page when you need a fast read on how STEVE-1 fits into the generative world model landscape, then validate the details in the benchmarks, citations, and related pages. - A key strength surfaced in the editorial record is handles diverse open-ended instructions. ## Editorial Trust Signals Editorial provenance and refresh policy preserved directly in static HTML. **Published by** world-models.io editorial board. **Lead editor** Tyler D. - Technical editor, methodology and benchmark analysis. This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource. Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-04-07. Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve. Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. [See the editorial policy.](https://world-models.io/en/editorial-policy/) Primary sources only Last reviewed date visible Methodology documented Source links included Correction channel published Review date visible ## External Sources Primary model and lab sources embedded in static HTML. - [STEVE-1 paper](https://arxiv.org/abs/2306.00937) UT Austin primary research source - [STEVE-1 official page](https://sites.google.com/view/steve-1) UT Austin official page - [UT Austin official website](https://www.cs.utexas.edu) Related lab ## References 1. [[1] Lifshitz et al., 2023. STEVE-1: A Generative Model for Text-to-Behavior in Minecraft. arXiv:2306.00937](https://arxiv.org/abs/2306.00937)