MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds
Not on the map. Why?
Abstract (arXiv)
We propose a new benchmark for planning tasks based on the Minecraft game. Our benchmark contains 45 tasks overall, but also provides support for creating both propositional and numeric instances of new Minecraft tasks automatically. We benchmark numeric and propositional planning systems on these tasks, with results demonstrating that state-of-the-art planners are currently incapable of dealing with many of the challenges advanced by our new benchmark, such as scaling to instances with thousands of objects. Based on these results, we identify areas of improvement for future planners. Our framework is made available at https://github.com/IretonLiu/mine-pddl/.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 10 of its 28 references that are in the map. First posted on arXiv 20 Dec 2023.
Builds on
10 of 28 references.
References · 10
- 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
- 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 215
- 2017Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundarycited by 58
- 2020PDDLGym: Gym Environments from PDDL Problemscited by 45
- 2020Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networkscited by 38
- 2019Learning Portable Representations for High-Level Planningcited by 11
- 2021The AI Settlement Generation Challenge in Minecraft: First Year Reportcited by 9
- 2021Classical Planning as QBF without Grounding (extended version)cited by 5
- 2023Hierarchically Composing Level Generators for the Creation of Complex Structurescited by 4
- 2020Task Scoping: Generating Task-Specific Abstractions for Planning in Open-Scope Modelscited by 1
Built on by
Citing papers per year: 2025: 5; 2026: 1.
6 papers.
- 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 40
- 2025TextAtari: 100K Frames Game Playing with Language Agentscited by 6
- 2025WGSR-Bench: Wargame-based Game-theoretic Strategic Reasoning Benchmark for Large Language Modelscited by 1
- 2025Lifted Successor Generation in Numeric Planningcited by 0
- 2025Dynamic Tree Databases in Automated Planningcited by 0
- 2026MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agentscited by 0
- 2026MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents9 Oct 2026
- 2025Dynamic Tree Databases in Automated Planning16 Nov 2025
- 2025Lifted Successor Generation in Numeric Planning1 Nov 2025
- 2025WGSR-Bench: Wargame-based Game-theoretic Strategic Reasoning Benchmark for Large Language Models12 Jun 2025
- 2025TextAtari: 100K Frames Game Playing with Language Agents4 Jun 2025
- 2025Large Language Models for Planning: A Comprehensive and Systematic Survey26 May 2025