Tag
This paper addresses the knowledge boundary problem in visual generation by introducing the SearchGen-20K benchmark and SearchGen-Corpus-1M, and proposes a teach-then-search co-training framework to handle evolving, long-tailed user requests beyond a generator's training data.
The article by Leonie Monigatti discusses the role of agentic search in context engineering for AI agents, tracing the evolution from fixed RAG pipelines to agentic RAG and context curation. It provides intuition on the strengths and weaknesses of various search tools used in agentic systems.