Tootfinder

End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
Qiaoyu Zheng, Yuze Sun, Chaoyi Wu, Weike Zhao, Pengcheng Qiu, Yongguo Yu, Kun Sun, Yanfeng Wang, Ya Zhang, Weidi Xie
https://arxiv.org/abs/2508.15746

End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
Accurate diagnosis with medical large language models is hindered by knowledge gaps and hallucinations. Retrieval and tool-augmented methods help, but their impact is limited by weak use of external knowledge and poor feedback-reasoning traceability. To address these challenges, We introduce Deep-DxSearch, an agentic RAG system trained end-to-end with reinforcement learning (RL) that enables steer tracebale retrieval-augmented reasoning for medical diagnosis. In Deep-DxSearch, we first construc…

Hard X-ray Contribution in AU Mic Flares and Its Minor Role in Atmospheric Escape
Yifan Hu, Murray Brightman, Fabio Favata, Haiwu Pan, Brian Grefenstette, Fiona A. Harrison, Daniel Stern, Weimin Yuan, Yuk L. Yung, Xiurui Zhao
https://arxiv.org/abs/2508.15107

Hard X-ray Contribution in AU Mic Flares and Its Minor Role in Atmospheric Escape
Flares from stars can significantly impact the atmospheres of their orbiting planets, yet the role of hard X-ray (HXR; 3-20 keV) emission in driving escape and tracing particle acceleration remains poorly constrained. With the aim of quantifying the HXR share of the total radiative budget, we obtained a NuSTAR observation, quasi-simultaneous with Swift and Einstein Probe observations, of the young M1Ve star AU Mic, detecting two flares. We build an empirical soft X-ray (SXR; 0.3-3 keV)-HXR scal…

Hysteresis Measurements as a Diagnostic Tool: A Systematic Approach for Stability Benchmarking and Performance Projection of 2D-Materials-Based MOSFETs
Alexander Karl, Dominic Waldhoer, Theresia Knobloch, Axel Verdianu, Jo\"el Kurzweil, Mina Bahrami, Mohammad Rasool Davoudi, Pedram Khakbaz, Bernhard Stampfer, Seyed Mehdi Sattari-Esfahlan, Yury Illarionov, Aftab Nazir, Changze Liu, Saptarshi Das, Xiao Renshaw Wang, Junchuan Tang, Yichi Zhang, Congwei Tan, Ye Li, Hailin Peng, Michae…

Hysteresis Measurements as a Diagnostic Tool: A Systematic Approach for Stability Benchmarking and Performance Projection of 2D-Materials-Based MOSFETs
Judging by its omnipresence in the literature, the hysteresis observed in the transfer characteristics of emerging transistors based on 2D-materials is widely accepted as an important metric related to the device quality. The hysteresis is often reported with attributes like "negligible" or "small" without giving any specifics as to how this was determined and against what reference the measured values were compared to. Quite surprisingly, there appears to be only a fragmentary understanding of…