CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916918225534976 |
|---|---|
| author | Chai, Qi Zheng, Zhang Ren, Junlong Ye, Deheng Lin, Zichuan Wang, Hao |
| author_facet | Chai, Qi Zheng, Zhang Ren, Junlong Ye, Deheng Lin, Zichuan Wang, Hao |
| contents | Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various in-game tasks. However, for complex tasks requiring lengthy sequences of actions, single-agent approaches often face challenges related to inefficiency and limited fault tolerance. Despite these issues, research on multi-agent collaboration remains scarce. In this paper, we propose CausalMACE, a holistic causality planning framework designed to enhance multi-agent systems, in which we incorporate causality to manage dependencies among subtasks. Technically, our proposed framework introduces two modules: an overarching task graph for global task planning and a causality-based module for dependency management, where inherent rules are adopted to perform causal intervention. Experimental results demonstrate our approach achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Chai, Qi Zheng, Zhang Ren, Junlong Ye, Deheng Lin, Zichuan Wang, Hao Artificial Intelligence Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various in-game tasks. However, for complex tasks requiring lengthy sequences of actions, single-agent approaches often face challenges related to inefficiency and limited fault tolerance. Despite these issues, research on multi-agent collaboration remains scarce. In this paper, we propose CausalMACE, a holistic causality planning framework designed to enhance multi-agent systems, in which we incorporate causality to manage dependencies among subtasks. Technically, our proposed framework introduces two modules: an overarching task graph for global task planning and a causality-based module for dependency management, where inherent rules are adopted to perform causal intervention. Experimental results demonstrate our approach achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft. |
| title | CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.18797 |