Agentic Tool Use in Large Language Models
This addresses the problem of fragmented research for researchers and practitioners in AI, but it is incremental as it organizes existing work rather than introducing new methods.
The paper tackles the fragmentation in studies of large language models as autonomous agents by organizing the literature into three paradigms—prompting as plug-and-play, supervised tool learning, and reward-driven tool policy learning—and analyzing their methods, strengths, and failure modes to provide a structured evolutionary view.
Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for information retrieval, computation and external action. Existing studies remain fragmented across tasks, tool types, and training settings, lacking a unified view of how tool-use methods differ and evolve. This paper organizes the literature into three paradigms: prompting as plug-and-play, supervised tool learning and reward-driven tool policy learning, analyzes their methods, strengths and failure modes, reviews the evaluation landscape and highlights key challenges, aiming to address this fragmentation and provide a more structured evolutionary view of agentic tool use.