# Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft

arXiv: https://arxiv.org/abs/2606.15684 · HTML: https://mlsanity.com/paper/2606.15684/

## Key facts

- Cited by 1 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 23 of its 27 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## 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, 23 of 23)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [MindAgent: Emergent Gaming Interaction](https://mlsanity.com/paper/2309.09971/) (2023)
- [Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2405.14314/) (2024)
- [ResearchTown: Simulator of Human Research Community](https://mlsanity.com/paper/2412.17767/) (2024)
- [VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft](https://mlsanity.com/paper/2406.05720/) (2024)
- [MCU: An Evaluation Framework for Open-Ended Game Agents](https://mlsanity.com/paper/2310.08367/) (2023)
- [SIMA 2: A Generalist Embodied Agent for Virtual Worlds](https://mlsanity.com/paper/2512.04797/) (2025)
- [JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse](https://mlsanity.com/paper/2503.16365/) (2025)
- [NitroGen: An Open Foundation Model for Generalist Gaming Agents](https://mlsanity.com/paper/2601.02427/) (2026)
- [Odyssey: Empowering Minecraft Agents with Open-World Skills](https://mlsanity.com/paper/2407.15325/) (2024)
- [TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft](https://mlsanity.com/paper/2412.05255/) (2024)
- [Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning](https://mlsanity.com/paper/2504.17950/) (2025)
- [MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs](https://mlsanity.com/paper/2403.19267/) (2024)
- [MineStudio: A Streamlined Package for Minecraft AI Agent Development](https://mlsanity.com/paper/2412.18293/) (2024)
- [Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2502.19717/) (2025)
- [BAMAS: Structuring Budget-Aware Multi-Agent Systems](https://mlsanity.com/paper/2511.21572/) (2025)
- [PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments](https://mlsanity.com/paper/2509.06235/) (2025)
- [AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints](https://mlsanity.com/paper/2512.11426/) (2025)

## Built on by (most cited first, 1 of 1)

- [GenCoord: Executable Commitments for Embodied LLM Agents under Private Information](https://mlsanity.com/paper/2608.22055/) (2026)

## 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.