Yong Liu

Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative think–search loop accumulates long system memories, leading...

Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adoption of LLMs-based agentic systems, access to structured data is increasingly instruction-driven, where relevance is...

Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained by a static, ''one-size-fits-all'' retrieval paradigm. Current systems fail to adaptively adjust the depth and breadth...

Generative recommendation casts recommendation as conditional sequence generation over text- or token-based representations and has shown strong promise in industrial systems. However, keeping such models up to date in dynamic environments is difficult: full retraining on sliding windows is expen...