AI RESEARCH
PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning
arXiv CS.LG
•
ArXi:2509.18169v3 Announce Type: replace Tasks on complex systems require high-precision numerical computation to decisions, but current large language models (LLMs) cannot integrate such computations as an intrinsic and interpretable capability with existing architectures. Multi-agent approaches can leverage external experts, but inevitably