Study finds grep search outperforms vector retrieval in LLM agent systems; accuracy depends heavily on tool-calling architecture and how results are presented to models.

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

View PDF HTML (experimental) Abstract:Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing adoption of retrieval-augmented generation (RAG) in agentic search systems, existing literature lacks a systematic comparison of how retrieval strategy choice interacts with agent architecture and tool-calling paradigm. Im...