# Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search

arXiv: https://arxiv.org/abs/2511.13885 · HTML: https://mlsanity.com/paper/2511.13885/

## Key facts

- Cited by 4 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 14 of its 29 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Seed1.5-VL Technical Report](https://mlsanity.com/paper/2505.07062/) (2025)
- [Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library](https://mlsanity.com/paper/2506.06122/) (2025)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning](https://mlsanity.com/paper/2508.08221/) (2025)
- [SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval](https://mlsanity.com/paper/2412.17250/) (2024)
- [TaoSR1: The Thinking Model for E-commerce Relevance Search](https://mlsanity.com/paper/2508.12365/) (2025)

## Built on by (most cited first, 4 of 4)

- [Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddings](https://mlsanity.com/paper/2601.11124/) (2026)
- [Reinforcement Fine-Tuning for History-Aware Dense Retriever in RAG](https://mlsanity.com/paper/2602.03645/) (2026)
- [SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce](https://mlsanity.com/paper/2608.19595/) (2026)
- [Learning to Retrieve via Reinforcement Learning in Embedding Space](https://mlsanity.com/paper/2610.07731/) (2026)

## Abstract (arXiv)

Dense retrieval, as the core component of e-commerce search engines, maps user queries and items into a unified semantic space through pre-trained embedding models to enable large-scale real-time semantic retrieval. Despite the rapid advancement of LLMs gradually replacing traditional BERT architectures for embedding, their training paradigms still adhere to BERT-like supervised fine-tuning and hard negative mining strategies. This approach relies on complex offline hard negative sample construction pipelines, which constrain model iteration efficiency and hinder the evolutionary potential of semantic representation capabilities. Besides, existing multi-task learning frameworks face the seesaw effect when simultaneously optimizing semantic relevance and non-relevance objectives. In this paper, we propose Retrieval-GRPO, a multi-objective reinforcement learning-based dense retrieval framework designed to address these challenges. The method eliminates offline hard negative sample construction by dynamically retrieving Top-K candidate products for each query during training, while introducing a relevance LLM as a reward model to generate real-time feedback. Specifically, the retrieval model dynamically optimizes embedding representations through reinforcement learning, with reward signals combining LLM-generated relevance scores, product quality scores, and multi-way exclusivity metrics to achieve multi-objective user preference alignment and real-time error correction. This mechanism not only removes dependency on hard negatives but also mitigates the seesaw effect through collaborative multi-objective optimization, significantly enhancing the model's semantic generalization capability for complex long-tail queries. Extensive offline and online experiments validate the effectiveness of Retrieval-GRPO, which has been deployed on China's largest e-commerce platform.