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

arXiv: https://arxiv.org/abs/2511.13726 · HTML: https://mlsanity.com/paper/2511.13726/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 21 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Chain of Thought Empowers Transformers to Solve Inherently Serial Problems](https://mlsanity.com/paper/2402.12875/) (2024)
- [Reasoning with Latent Thoughts: On the Power of Looped Transformers](https://mlsanity.com/paper/2502.17416/) (2025)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [A Survey on Latent Reasoning](https://mlsanity.com/paper/2507.06203/) (2025)
- [Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models](https://mlsanity.com/paper/2411.12580/) (2024)
- [Reinforcement Pre-Training](https://mlsanity.com/paper/2506.08007/) (2025)
- [RLP: Reinforcement as a Pretraining Objective](https://mlsanity.com/paper/2510.01265/) (2025)
- [Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings](https://mlsanity.com/paper/2506.15001/) (2025)

## Built on by (most cited first, 2 of 2)

- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2603.17387/) (2026)

## Abstract (arXiv)

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.