Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913050763722752 |
|---|---|
| author | Jian, HuaDong Li, Chenghao Wang, Haoyu Shuai, Jiajia Guo, Jinyu Yang, Yang Zhang, Chaoning |
| author_facet | Jian, HuaDong Li, Chenghao Wang, Haoyu Shuai, Jiajia Guo, Jinyu Yang, Yang Zhang, Chaoning |
| contents | In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination noise, interrupts local execution, and overuses public interaction in cases that could be resolved locally. To address this issue, we propose a partitioned information architecture for MLLM agents that explicitly separates private execution states from public coordination states. Building on this design, we introduce two key mechanisms. First, we develop an event-triggered working memory based on system-verified outcomes to maintain compact and low-noise local state representations. Second, we propose a cost-sensitive gated escalation mechanism that determines whether cross-region communication should be initiated by jointly considering node criticality, local recovery cost, and downstream task impact. In this way, communication is transformed from a default reaction into a selective decision. Experiments conducted on long-term construction tasks in open environments demonstrate that, compared to baseline models based on strong communication and planned structures, the introduction of gated communication and a partitioned information architecture results in superior performance in terms of blueprint completion quality and execution chain length. It also improves local self-recovery, reduces ineffective escalations, and increases the utility of public communication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18975 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game Jian, HuaDong Li, Chenghao Wang, Haoyu Shuai, Jiajia Guo, Jinyu Yang, Yang Zhang, Chaoning Multiagent Systems In long-horizon open-world multi-agent systems, existing methods often treat local anomalies as automatic triggers for communication. This default design introduces coordination noise, interrupts local execution, and overuses public interaction in cases that could be resolved locally. To address this issue, we propose a partitioned information architecture for MLLM agents that explicitly separates private execution states from public coordination states. Building on this design, we introduce two key mechanisms. First, we develop an event-triggered working memory based on system-verified outcomes to maintain compact and low-noise local state representations. Second, we propose a cost-sensitive gated escalation mechanism that determines whether cross-region communication should be initiated by jointly considering node criticality, local recovery cost, and downstream task impact. In this way, communication is transformed from a default reaction into a selective decision. Experiments conducted on long-term construction tasks in open environments demonstrate that, compared to baseline models based on strong communication and planned structures, the introduction of gated communication and a partitioned information architecture results in superior performance in terms of blueprint completion quality and execution chain length. It also improves local self-recovery, reduces ineffective escalations, and increases the utility of public communication. |
| title | Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2604.18975 |