AI RESEARCH

ParaTool: Shifting Tool Representations from Context to Parameters

arXiv CS.AI

ArXi:2605.29561v1 Announce Type: new Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby ing environment-coupled problem solving. However, mainstream in-context learning (ICL) approaches typically incorporate detailed tool documentation and usage examples directly into the context. This results in substantial inference overhead and heightened risks of hallucination as the context length grows.