DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks

Abstract: This work enhances the ability of LLMs to perform complex reasoning in 3D scenes. Recent work has addressed the 3D situated reasoning task by invoking tool usage through LLMs. LLMs call tools via APIs and integrate the generated programs through a chain of thought to solve problems based on the program results. However, due to the simplicity of the questions in the dataset, the generated program reasoning chains are relatively short. To solve this main challenge, in this paper, we introduce DeepThink3D to enhance the tool usage of LLMs in complex 3D situated reasoning tasks. Our work proposes a combinatorial and iterative evolutionary approach on the SQA3D benchmark to generate more complex questions. Building on this foundation, we fine-tune the LLM to make it more proficient in using 3D tools. By employing Direct Preference Optimization (DPO), we directly optimize the toolchain strategies generated by models, thereby enhancing their accuracy in complex tasks.