Disentangling Reasoning and Knowledge in Medical Large Language Models

Medical reasoning in large language models (LLMs) aims to emulate clinicians' diagnostic thinking, but current benchmarks such as MedQA-USMLE, MedMCQA, and PubMedQA often mix reasoning with factual recall. We address this by separating 11 biomedical QA benchmarks into reasoning- and knowledge-focused subsets using a PubMedBERT classifier that reaches 81 percent accuracy, comparable to human performance. Our analysis shows that only 32.8 percent of questions require complex reasoning. We evaluate biomedical models (HuatuoGPT-o1, MedReason, m1) and general-domain models (DeepSeek-R1, o4-mini, Qwen3), finding consistent gaps between knowledge and reasoning performance. For example, m1 scores 60.5 on knowledge but only 47.1 on reasoning. In adversarial tests where models are misled with incorrect initial reasoning, biomedical models degrade sharply, while larger or RL-trained general models show more robustness. To address this, we train BioMed-R1 using fine-tuning and reinforcement learning on reasoning-heavy examples. It achieves the strongest performance among similarly sized models. Further gains may come from incorporating clinical case reports and training with adversarial and backtracking scenarios.

Analytical Solution for Inverse Kinematics

This paper introduces a closed-form analytical solution for the inverse kinematics (IK) of a 6 Degrees of Freedom (DOF) serial robotic manipulator arm, configured with six revolute joints and utilized within the Lunar Exploration Rover System (LERS). As a critical asset for conducting precise operations in the demanding lunar environment, this robotic arm relies on the IK solution to determine joint parameters required for precise end-effector positioning, essential for tasks such as sample collection, infrastructure assembly, and equipment deployment. By applying geometric principles, the proposed method offers a highly efficient and accurate approach to solving the IK problem, significantly reducing computational demands compared to traditional numerical methods. This advancement not only enhances real-time operational capabilities but is also optimized for space robotics, where precision and speed are critical. Additionally, the paper explores the integration of the LERS robotic system, underscoring the importance of this work in supporting autonomous lunar exploration within the ARTEMIS program and future missions