Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft
On the map: LLM agents and tool use → Reinforcement learning for LLM agents
Abstract (arXiv)
We present TickingCollabBench, a Minecraft-based multi-agent benchmark for a novel class of time-sensitive complementary collaboration tasks. Our benchmark reflects four core characteristics of real-world collaboration: agent heterogeneity, mandatory collaboration, dynamic environments, and strict real-time constraints with failure risks. To enable this, we develop the TickingCollab framework, which supports the generation of diverse dynamic environments and abstracts Minecraft's primitive APIs to enable declarative YAML task specifications for composing these events. Building on this, we design a feasibility-aware automated benchmark generation pipeline, where an LLM drafts structurally diverse task configurations and feasibility verifier filters out invalid ones using approximate constraints. Evaluations demonstrate that lang latency and inherent difficulty of coordinating under partial observability and agent heterogeneity cause LLMs to frequently fail under dynamic environments and fall significantly short of a global-knowledge oracle.
Key facts. Cited by 1 paper 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 23 of its 27 references that are in the map. First posted on arXiv 14 Jun 2026.
Builds on
23 of 27 references.
Closest ancestors · 8
Same direction, newest first
- 2026NitroGen: An Open Foundation Model for Generalist Gaming Agents4 Jan
- 2025SIMA 2: A Generalist Embodied Agent for Virtual Worlds4 Dec
- 2025PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments7 Sep
- 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning24 Apr
- 2024Odyssey: Empowering Minecraft Agents with Open-World Skills22 Jul
- 2024MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs28 Mar
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May
- 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge17 Jun
Other references · 15
- 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
- 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
- 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 215
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
- 2023MindAgent: Emergent Gaming Interactioncited by 88
- 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
- 2024ResearchTown: Simulator of Human Research Communitycited by 37
- 2024VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraftcited by 35
- 2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 34
- 2025JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mousecited by 28
- 2024TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraftcited by 21
- 2024MineStudio: A Streamlined Package for Minecraft AI Agent Developmentcited by 13
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
- 2026MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability
- 2026MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents
- 2026Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
- 2025Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft
- 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems
- 2026MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
- 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation