Chuanbo Zhu

AUG 19, 2026 · PREPRINT

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

arXiv

This is an unpeer-reviewed arXiv preprint describing a machine learning framework for LLM tool-calling; it has not undergone peer review and reports only computational benchmarks without clinical or human validation.

AUG 19, 2026 · PREPRINT

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

arXiv

This is an early-stage machine learning method paper presenting a novel framework without peer review, demonstrating proof-of-concept across benchmarks but lacking independent validation or clinical applicability.