Latent Preference Modeling for Multi-Session Personalized Tool Calling
Quick summary
arXiv:2604.17886v2 Announce Type: replace-cross Abstract: 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 in a more realistic setup, we present Multi-Session Personalized Tool Calling (MPT), a benchmark comprising 4,695 instances over 459 multi-session interaction histories that cover three challenges: Preference Recall, Inductio
Key takeaways
- arXiv:2604.17886v2 Announce Type: replace-cross Abstract: 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 in a more realistic setup, we present Multi-Session Personalized Tool Calling (MPT), a benchmark comprising 4,695 instances over 459 multi-session interaction histories that cover three challenges: Preference Recall, Inductio
Why it matters
“Latent Preference Modeling for Multi-Session Personalized Tool Calling” is a product decision that may change how people work with AI. Its value depends on task completion, correction effort and data handling—not simply the presence of a new feature.
Member comments