Search papers, labs, and topics across Lattice.
The paper addresses the problem of LLMs failing in real-world tool interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent by introducing a curriculum-inspired framework that uses structured reasoning templates. This framework guides LLMs through step-by-step instructions for generating function calls, improving their understanding of user goals and tool documentation. Experiments demonstrate a 3-12% relative improvement in tool-use accuracy compared to strong baselines, while also enhancing robustness, interpretability, and transparency.
Free-form Chain-of-Thought prompting actually *hurts* LLMs when it comes to structured function-calling tasks, but a guided-structured template approach boosts tool-use accuracy by up to 12%.
Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities, yet they often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent. These issues often stem from an incomplete understanding of user goals and inadequate comprehension of tool documentation. While Chain-of-Thought (CoT) prompting has proven effective for enhancing reasoning in general contexts, our analysis reveals that free-form CoT is insufficient and sometimes counterproductive for structured function-calling tasks. To address this, we introduce a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function callings. Experimental results show that our method reduces tool-use errors, achieving 3-12% relative improvements over strong baselines across diverse model series and approaches. Moreover, our framework enhances the robustness, interpretability, and transparency of tool-using agents, advancing the development of more reliable AI assistants for real-world applications.