BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhan, Yu-Wei, Wang, Xin, Mao, Pengzhe, Feng, Tongtong, Wang, Ren, Zhu, Wenwu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915653345083392
author Zhan, Yu-Wei
Wang, Xin
Mao, Pengzhe
Feng, Tongtong
Wang, Ren
Zhu, Wenwu
author_facet Zhan, Yu-Wei
Wang, Xin
Mao, Pengzhe
Feng, Tongtong
Wang, Ren
Zhu, Wenwu
contents Building generalist embodied agents requires a unified system that can interpret multimodal goals, model environment dynamics, and execute reliable actions across diverse real-world tasks. Multimodal large language models (MLLMs) offer strong semantic priors and cross-modal generalization, while world models (WMs) provide actionable latent dynamics for prediction and control. Their combination holds promise for open-ended embodied intelligence, yet introduces two key challenges: (1) establishing a tight coupling between the semantic intent from MLLMs and the dynamic state representations within the WM's latent space, and (2) achieving task-aware adaptability that supports multi-task learning and cross-environment generalization. To address these limitations, we propose BiTAgent, a task-aware dynamic joint framework that enables bidirectional coupling between MLLMs and WMs. BiTAgent establishes two complementary pathways: a forward path that injects MLLM representations into the WM's latent space for semantically guided imagination, and a backward path where WM-generated feedback refines the MLLM's semantic space via dense text-conditioned rewards. This bidirectional interaction is realized through three synergistic components: Task-Aware Dynamic Joint Learning, Task-Aware Behavior Learning, and MLLM-WM Joint Optimization, which together harmonize semantic reasoning and dynamic prediction. Extensive experiments across multi-task and cross-environment settings demonstrate superior stability and generalization over state-of-the-art baselines, marking a step toward open-ended embodied learning.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04513
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models
Zhan, Yu-Wei
Wang, Xin
Mao, Pengzhe
Feng, Tongtong
Wang, Ren
Zhu, Wenwu
Artificial Intelligence
Building generalist embodied agents requires a unified system that can interpret multimodal goals, model environment dynamics, and execute reliable actions across diverse real-world tasks. Multimodal large language models (MLLMs) offer strong semantic priors and cross-modal generalization, while world models (WMs) provide actionable latent dynamics for prediction and control. Their combination holds promise for open-ended embodied intelligence, yet introduces two key challenges: (1) establishing a tight coupling between the semantic intent from MLLMs and the dynamic state representations within the WM's latent space, and (2) achieving task-aware adaptability that supports multi-task learning and cross-environment generalization. To address these limitations, we propose BiTAgent, a task-aware dynamic joint framework that enables bidirectional coupling between MLLMs and WMs. BiTAgent establishes two complementary pathways: a forward path that injects MLLM representations into the WM's latent space for semantically guided imagination, and a backward path where WM-generated feedback refines the MLLM's semantic space via dense text-conditioned rewards. This bidirectional interaction is realized through three synergistic components: Task-Aware Dynamic Joint Learning, Task-Aware Behavior Learning, and MLLM-WM Joint Optimization, which together harmonize semantic reasoning and dynamic prediction. Extensive experiments across multi-task and cross-environment settings demonstrate superior stability and generalization over state-of-the-art baselines, marking a step toward open-ended embodied learning.
title BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models
topic Artificial Intelligence
url https://arxiv.org/abs/2512.04513