Search-R3: Unifying Reasoning and Embedding in Large Language Models

ArXi:2510.07048v2 Announce Type: replace Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to generate search embeddings as a direct output of their reasoning process. Our approach exploits LLMs' chain-of-thought capabilities, allowing them to produce effective embeddings by reasoning step-by-step through complex semantic analyses. We implement this through three complementary mechanisms.