Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning

We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models.

The method obtains the final semantic representation by running multiple forward passes of the text embedding model.

Experiments show that RT achieves significant improvements on semantic reasoning tasks in BRIGHT and the person-job matching benchmark PJBenchmark, while maintaining consistent performance on general-purpose semantic understanding tasks such as C-MTEB.

Our results indicate that RT is effective because it further activates the semantic reasoning ability learned during pretraining by decoder-only text embedding models (e.g., Qwen3-Embedding-8B).

RT can be seen as a test-time inference method.