AI RESEARCH

Latent Preference Modeling for Cross-Session Personalized Tool Calling

arXiv CS.CL

ArXi:2604.17886v1 Announce Type: new Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete arguments, highlighting the need for personalized tool calling. To study this problem, we