TAMA: Tool-Augmented Multimodal Agent for Procedural Activity Understanding
This work addresses the development of procedural activity assistants for applications in daily life and professional settings, representing an incremental advancement in multimodal reasoning.
The paper tackles procedural activity understanding by proposing TAMA, a tool-augmented multimodal agent that improves performance on the ProMQA-Assembly dataset, enhancing vision-language models like GPT-5 and MiMo-VL.
Procedural activity assistants potentially support humans in a variety of settings, from our daily lives, e.g., cooking or assembling flat-pack furniture, to professional situations, e.g., manufacturing or biological experiments. Despite its potential use cases, the system development tailored for such an assistant is still underexplored. In this paper, we propose a novel framework, called TAMA, a Tool-Augmented Multimodal Agent, for procedural activity understanding. TAMA enables interleaved multimodal reasoning by making use of multimedia-returning tools in a training-free setting. Our experimental result on the multimodal procedural QA dataset, ProMQA-Assembly, shows that our approach can improve the performance of vision-language models, especially GPT-5 and MiMo-VL. Furthermore, our ablation studies provide empirical support for the effectiveness of two features that characterize our framework, multimedia-returning tools and agentic flexible tool selection. We believe our proposed framework and experimental results facilitate the thinking with images paradigm for video and multimodal tasks, let alone the development of procedural activity assistants.