VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft

TL;DR

This paper introduces VillagerAgent, a graph-based multi-agent framework designed to handle complex task dependencies in Minecraft, validated on a new benchmark called VillagerBench, and demonstrating superior performance over existing models.

Contribution

The paper presents VillagerAgent, a novel DAG-based multi-agent framework with a task decomposer, controller, and state manager, along with a new benchmark for evaluating multi-agent collaboration.

Findings

VillagerAgent outperforms AgentVerse in task decomposition.

VillagerBench effectively tests multi-agent collaboration in complex scenarios.

VillagerAgent reduces hallucinations and improves efficiency.

Abstract

In this paper, we aim to evaluate multi-agent systems against complex dependencies, including spatial, causal, and temporal constraints. First, we construct a new benchmark, named VillagerBench, within the Minecraft environment.VillagerBench comprises diverse tasks crafted to test various aspects of multi-agent collaboration, from workload distribution to dynamic adaptation and synchronized task execution. Second, we introduce a Directed Acyclic Graph Multi-Agent Framework VillagerAgent to resolve complex inter-agent dependencies and enhance collaborative efficiency. This solution incorporates a task decomposer that creates a directed acyclic graph (DAG) for structured task management, an agent controller for task distribution, and a state manager for tracking environmental and agent data. Our empirical evaluation on VillagerBench demonstrates that VillagerAgent outperforms the existing AgentVerse model, reducing hallucinations and improving task decomposition efficacy. The results underscore VillagerAgent's potential in advancing multi-agent collaboration, offering a scalable and generalizable solution in dynamic environments. The source code is open-source on GitHub (https://github.com/cnsdqd-dyb/VillagerAgent).