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' perceiving tool-use ability 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 visual- or auditory-grounded instructions' information. Therefore, in this paper, we propose Tool-LMM, a system incorporating open-source LLMs and multi-modal encoders so that the learnt 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 featured by consisting of multi-modal input tools from HuggingFace. Another important feature of our dataset is that our dataset 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 LMM is capable of recommending appropriate tools for multi-modal instructions. Codes and data are available at https://github.com/Tool-LMM/Tool-LMM.

翻译：近期，大型语言模型（LLMs）在自然语言理解与生成任务中展现出惊人性能，这促使大量研究探索将其作为核心控制器来构建智能体系统。多项研究聚焦于将LLMs与外部工具连接以扩展应用场景。然而，当前LLMs感知工具使用的能力局限于单一文本查询，这可能导致对用户真实意图的理解存在歧义。研究者期望通过让LLMs感知视觉或听觉导向指令中的信息来消除这一问题。为此，本文提出Tool-LMM系统，该系统整合了开源LLMs与多模态编码器，使经过学习的LLMs能够感知多模态输入指令并正确选择功能匹配的工具。为便于评估模型能力，我们收集了一个包含来自HuggingFace的多模态输入工具数据集。该数据集的另一重要特征是：由于存在功能相同与同义功能的情况，数据集中同一指令包含多个潜在选择，为相同查询提供了更多可行方案。实验表明，我们的多模态大模型（LMM）能够为多模态指令推荐合适的工具。代码与数据已开源至https://github.com/Tool-LMM/Tool-LMM。