We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted $k$-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The system runs inside an iterative Neural-Socratic Graph Dialogue loop in which concise diagnostic messages produced by the language model are mapped to targeted graph edits or seed expansions, enabling adaptive retrieval when the model expresses uncertainty. This combination yields a retrieval mechanism that is both token-efficient and topology-aware while preserving interpretable path-level traces for diagnostics and intervention. We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses. The results demonstrate consistent improvements in answer accuracy, evidence coverage, and end-to-end efficiency compared to strong graph- and LLM-based baselines. We further analyze trade-offs between semantic weighting, verifier filtering, and iterative updates, and report practical recommendations for deployment under constrained compute and token budgets.

This paper proposes a memory-enhanced framework for object identification in Cryo-Electron Tomography (Cryo-ET) data, integrating a distance transform-based loss function and multi-scale test-time augmentation (TTA). The method addresses critical challenges in Cryo-ET segmentation, such as low signal-to-noise ratio (SNR$\mathrm{F}_{\beta}-4$score over baseline models. Ablation studies validate the contributions of each component, with the memory module and distance loss providing 2.51% and 1.65% gains, respectively. The integration of robotic technologies in Cryo-ET data acquisition and analysis further enhances experimental automation, enabling more efficient and accurate data processing. This has significant potential in automated biomedical research, particularly in robotics-assisted Cryo-ET workflows for high-precision biological studies.