Large language models (LLMs) have acquired substantial medical knowledge and reasoning skills during pretraining, yet eliciting these capabilities typically requires scarce rationales or costly post-training. To address this gap, we introduce **RIPT**, a lightweight framework for data-efficient endogenous capability activation. It explicitly decomposes this objective into two complementary components: reasoning enhancement and medical knowledge elicitation. For the former, we extract steering vectors from hidden activations on a small set of high-quality paired reasoning and vanilla responses to shape LLMs’ reasoning behavior. For the latter, we obtain prefix vectors via prefix tuning on simple medical QA pairs to elicit domain-specific knowledge. At inference, RIPT freezes the backbone LLM and combines steering-vector injection with prefix-vector conditioning. Rather than injecting external knowledge, RIPT aims to unlock medical reasoning capabilities already acquired by LLMs during pretraining. Experiments under limited-resource settings show that RIPT consistently improves diverse backbone LLMs and benchmarks, suggesting a generalizable pathway for lightweight medical reasoning enhancement.

Clinical decision-making agents can benefit from structured reuse of prior decision experience. Motivated by illness scripts, we study how to organize clinical experiences with explicit applicability conditions and inter-experience relations. However, many memory-augmented methods store experiences as independent records without conditional or relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that formalizes experiences as indications and contraindications and organizes them into a dual-layer memory graph. GSEM captures both intra-experience decision structure and inter-experience dependencies, supporting applicability-aware retrieval and feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90% and 69.24% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/unname797/gsem.