MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
This addresses the problem of ambiguous tool selection in agent systems for users relying on multi-modal instructions, but it is incremental as it builds on existing LLM and multi-modal integration approaches.
The paper tackles the problem of large language models (LLMs) having limited ability to perceive tool use from single text queries, which can cause ambiguity in understanding user intentions, by proposing MLLM-Tool, a system that incorporates open-source LLMs and multi-modal encoders to enable LLMs to handle multi-modal input instructions and select function-matched tools correctly, with experiments showing it is capable of recommending appropriate tools for multi-modal instructions.
Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' ability to perceive tool use is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the information in the visual- or auditory-grounded instructions. Therefore, in this paper, we propose MLLM-Tool, a system incorporating open-source LLMs and multi-modal encoders so that the learned LLMs can be conscious of multi-modal input instruction and then select the function-matched tool correctly. To facilitate the evaluation of the model's capability, we collect a dataset featuring multi-modal input tools from HuggingFace. Another essential feature of our dataset is that it also contains multiple potential choices for the same instruction due to the existence of identical functions and synonymous functions, which provides more potential solutions for the same query. The experiments reveal that our MLLM-Tool is capable of recommending appropriate tools for multi-modal instructions. Codes and data are available at https://github.com/MLLM-Tool/MLLM-Tool.