Salvato in:
Dettagli Bibliografici
Autori principali: Fu, Honghao, Ren, Junlong, Chai, Qi, Ye, Deheng, Cai, Yujun, Wang, Hao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.18722
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911499759386624
author Fu, Honghao
Ren, Junlong
Chai, Qi
Ye, Deheng
Cai, Yujun
Wang, Hao
author_facet Fu, Honghao
Ren, Junlong
Chai, Qi
Ye, Deheng
Cai, Yujun
Wang, Hao
contents Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments. Nonetheless, their performance is hindered by the absence of domain-specific knowledge. Methods that finetune on large-scale domain-specific data entail prohibitive development costs. This paper introduces VistaWise, a cost-effective agent framework that integrates cross-modal domain knowledge and finetunes a dedicated object detection model for visual analysis. It reduces the requirement for domain-specific training data from millions of samples to a few hundred. VistaWise integrates visual information and textual dependencies into a cross-modal knowledge graph (KG), enabling a comprehensive and accurate understanding of multimodal environments. We also equip the agent with a retrieval-based pooling strategy to extract task-related information from the KG, and a desktop-level skill library to support direct operation of the Minecraft desktop client via mouse and keyboard inputs. Experimental results demonstrate that VistaWise achieves state-of-the-art performance across various open-world tasks, highlighting its effectiveness in reducing development costs while enhancing agent performance.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft
Fu, Honghao
Ren, Junlong
Chai, Qi
Ye, Deheng
Cai, Yujun
Wang, Hao
Artificial Intelligence
Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments. Nonetheless, their performance is hindered by the absence of domain-specific knowledge. Methods that finetune on large-scale domain-specific data entail prohibitive development costs. This paper introduces VistaWise, a cost-effective agent framework that integrates cross-modal domain knowledge and finetunes a dedicated object detection model for visual analysis. It reduces the requirement for domain-specific training data from millions of samples to a few hundred. VistaWise integrates visual information and textual dependencies into a cross-modal knowledge graph (KG), enabling a comprehensive and accurate understanding of multimodal environments. We also equip the agent with a retrieval-based pooling strategy to extract task-related information from the KG, and a desktop-level skill library to support direct operation of the Minecraft desktop client via mouse and keyboard inputs. Experimental results demonstrate that VistaWise achieves state-of-the-art performance across various open-world tasks, highlighting its effectiveness in reducing development costs while enhancing agent performance.
title VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft
topic Artificial Intelligence
url https://arxiv.org/abs/2508.18722