The field of question answering and de novo peptide sequencing is rapidly evolving, with a focus on integrating knowledge graphs and large language models to improve accuracy and efficiency. Recent developments have led to the creation of novel frameworks that combine retrieval-augmented generation with semantic vector retrieval, enabling more precise and context-aware responses. Additionally, advancements in de novo peptide sequencing have resulted in the development of new computational paradigms that impute missing fragmentation information, leading to significant improvements in performance. Notably, the use of latent imputation and reranking strategies has shown great promise in enhancing the accuracy of peptide sequencing. Furthermore, research in claim verification has led to the development of frameworks that leverage knowledge graphs and large language models to improve the verification process, particularly in cases with complex semantic structures or obfuscated entities. Some notable papers in this area include DO-RAG, which proposes a scalable and customizable hybrid QA framework, and LIPNovo, which introduces a novel computational paradigm for de novo peptide sequencing. Hydra is also noteworthy, as it presents a training-free framework that unifies graph topology, document semantics, and source reliability to support deep reasoning in large language models. Overall, these advancements have the potential to significantly impact the field of question answering and de novo peptide sequencing, enabling more accurate and efficient solutions for complex problems.