MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft

• URL: http://arxiv.org/abs/2605.30931v1
• Date: Fri, 29 May 2026 07:21:47 GMT
• Title: MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
• Abstract summary: We introduce MineExplorer benchmark for evaluating open-world exploration capabilities of MLLM agents in Minecraft.<n>We first filter atomic tasks whose solutions rely heavily on Minecraft-specific knowledge to better reflect general open-world reasoning.<n>We use a multi-agent synthesis workflow that jointly designs task graphs, sandbox scenes, and rule-based milestone evaluators.
• Score: 33.74405061496877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic open worlds remains unclear. Existing embodied and game-based benchmarks often compress interaction into short-horizon tasks or entangle success with domain-specific game mechanics. In this paper, we introduce MineExplorer benchmark for evaluating open-world exploration capabilities of MLLM agents in Minecraft. We first filter atomic tasks whose solutions rely heavily on Minecraft-specific knowledge to better reflect general open-world reasoning. Then we organize the benchmark around a ReAct-style capability formulation and compose atomic tasks into implicit multi-hop tasks. To further construct reliable instances, MineExplorer uses a multi-agent synthesis workflow that jointly designs task graphs, sandbox scenes, and rule-based milestone evaluators. Human evaluation shows that the multi-agent synthesis workflow produces significantly more reliable instances than a single-agent baseline. Experiments with advanced MLLM agents show that open-world exploration remains challenging, as strong models can handle many single-hop tasks but degrade sharply when hidden prerequisites must be coordinated over longer trajectories. Further analysis finds that task difficulty tracks agent completion, and larger models or thinking modes do not consistently translate into better performance. Code and dataset are available at https://github.com/Jometeorie/MineExplorer.

Related papers

• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios [63.67884284105684]
  We introduce textbfUltraHorizon, a novel benchmark that measures the foundational capabilities essential for complex real-world challenges.<n>Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules.<n>Our experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores.
  arXiv  Detail & Related papers  (2025-09-26T02:04:00Z)
• Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts [54.21319853862452]
  We present Optimus-3, a general-purpose agent for Minecraft.<n>We propose a knowledge-enhanced data generation pipeline to provide scalable and high-quality training data for agent development.<n>We develop a Multimodal Reasoning-Augmented Reinforcement Learning approach to enhance the agent's reasoning ability for visual diversity.
  arXiv  Detail & Related papers  (2025-06-12T05:29:40Z)
• Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks [94.19506319646376]
  We introduce Agent-X, a benchmark for evaluating vision-centric agents in real-world, multimodal settings.<n>Agent-X features 828 agentic tasks with authentic visual contexts, including images, multi-image comparisons, videos, and instructional text.<n>Our results reveal that even the best-performing models, including GPT, Gemini, and Qwen families, struggle to solve multi-step vision tasks.
  arXiv  Detail & Related papers  (2025-05-30T17:59:53Z)
• EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability [11.721839449847472]
  We introduce MM-Escape, a benchmark for investigating multimodal reasoning.<n> MM-Escape emphasizes intermediate model behaviors alongside final task completion.<n>Extensive experiments show that MLLMs, regardless of scale, can successfully complete the simplest room escape tasks.<n>We observe that performance bottlenecks vary across models, revealing distinct failure modes and limitations in their multimodal reasoning abilities.
  arXiv  Detail & Related papers  (2025-03-13T04:48:43Z)
• Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy [50.13429055093534]
  Optimus-2 is a novel Minecraft agent that incorporates a Multimodal Large Language Model (MLLM) for high-level planning.<n>We introduce a high-quality Minecraft Goal-Observation-Action (MGOA) dataset, which contains 25,000 videos across 8 atomic tasks.<n>Optimus-2 exhibits superior performance across atomic tasks, long-horizon tasks, and open-ended instruction tasks in Minecraft.
  arXiv  Detail & Related papers  (2025-02-27T09:18:04Z)
• TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft [40.419794780178044]
  We present TeamCraft, a multi-modal multi-agent benchmark built on top of the open-world video game Minecraft.<n>The benchmark features 55,000 task variants specified by multi-modal prompts, procedurally-generated expert demonstrations for imitation learning, and carefully designed protocols to evaluate model generalization capabilities.<n>Our results indicate that existing models continue to face significant challenges in generalizing to novel goals, scenes, and unseen numbers of agents.
  arXiv  Detail & Related papers  (2024-12-06T18:41:16Z)
• Odyssey: Empowering Minecraft Agents with Open-World Skills [26.537984734738764]
  We introduce Odyssey, a new framework that empowers Large Language Model (LLM)-based agents with open-world skills to explore the vast Minecraft world.<n>Odyssey comprises three key parts: (1) An interactive agent with an open-world skill library that consists of 40 primitive skills and 183 compositional skills; (2) A fine-tuned LLaMA-3 model trained on a large question-answering dataset with 390k+ instruction entries derived from the Minecraft Wiki; and (3) A new agent capability benchmark.
  arXiv  Detail & Related papers  (2024-07-22T02:06:59Z)
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory [97.87093169454431]
  Ghost in the Minecraft (GITM) is a novel framework that integrates Large Language Models (LLMs) with text-based knowledge and memory. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate.
  arXiv  Detail & Related papers  (2023-05-25T17:59:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.