The field of conversational search is moving towards more robust and efficient systems, with a focus on resolving ambiguity and handling fuzzy user intent. Recent developments have shown that techniques such as query rewriting, retrieval fusion, and large language models can improve the accuracy and effectiveness of conversational search systems. Additionally, there is a growing interest in incorporating commonsense knowledge and contextual understanding into these systems to better handle ambiguous references and user requests. Noteworthy papers include: CFDA & CLIP at TREC iKAT 2025, which explored query rewriting and retrieval fusion to improve robustness and efficiency in conversational search. It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge, which investigated the ability of large language models to resolve referential ambiguity in multi-turn conversations. From What to Eat? to Perfect Recipe: ChefMind's Chain-of-Exploration for Ambiguous User Intent in Recipe Recommendation, which proposed a hybrid architecture for personalized recipe recommendation that combines chain of exploration, knowledge graph, retrieval-augmented generation, and large language models. Interactive Real-Time Speaker Diarization Correction with Human Feedback, which developed an LLM-assisted speaker diarization correction system that enables users to fix speaker attribution errors in real-time. BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents, which introduced a user-centric search evaluation method that uses large language models to generate fine-grained user intents and evaluate search results against each intent. Do LLMs Encode Frame Semantics? Evidence from Frame Identification, which investigated whether large language models encode latent knowledge of frame semantics and can perform frame identification effectively. Retrieval Augmented Generation based context discovery for ASR, which proposed an efficient embedding-based retrieval approach for automatic context discovery in context-aware automatic speech recognition systems. Learning Contextual Retrieval for Robust Conversational Search, which proposed a novel LLM-based retriever that directly incorporates conversational context into the retrieval process.