# TaoSR1: The Thinking Model for E-commerce Relevance Search

arXiv: https://arxiv.org/abs/2508.12365 · HTML: https://mlsanity.com/paper/2508.12365/

## Key facts

- Cited by 10 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 16 of its 33 references that are in the map.
- First posted on arXiv 17 Aug 2025.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2504.13914/) (2025)
- [Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library](https://mlsanity.com/paper/2506.06122/) (2025)
- [Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.16188/) (2025)
- [Large Language Models for Relevance Judgment in Product Search](https://mlsanity.com/paper/2406.00247/) (2024)
- [GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets](https://mlsanity.com/paper/2504.19898/) (2025)
- [Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting](https://mlsanity.com/paper/2408.09439/) (2024)
- [Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm](https://mlsanity.com/paper/2108.05652/) (2021)

## Built on by (most cited first, 10 of 10)

- [Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm](https://mlsanity.com/paper/2510.14321/) (2025)
- [Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search](https://mlsanity.com/paper/2511.13885/) (2025)
- [Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance](https://mlsanity.com/paper/2601.21611/) (2026)
- [LORE: A Large Generative Model for Search Relevance](https://mlsanity.com/paper/2512.03025/) (2025)
- [K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance](https://mlsanity.com/paper/2604.25683/) (2026)
- [Valley3: Scaling Omni Foundation Models for E-commerce](https://mlsanity.com/paper/2605.01278/) (2026)
- [Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction](https://mlsanity.com/paper/2601.03672/) (2026)
- [RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance](https://mlsanity.com/paper/2605.25486/) (2026)
- [Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance](https://mlsanity.com/paper/2605.31003/) (2026)
- [SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce](https://mlsanity.com/paper/2608.19595/) (2026)

## Abstract (arXiv)

Query-product relevance prediction is a core task in e-commerce search. BERT-based models excel at semantic matching but lack complex reasoning capabilities. While Large Language Models (LLMs) are explored, most still use discriminative fine-tuning or distill to smaller models for deployment. We propose a framework to directly deploy LLMs for this task, addressing key challenges: Chain-of-Thought (CoT) error accumulation, discriminative hallucination, and deployment feasibility. Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning (SFT) with CoT to instill reasoning; (2) Offline sampling with a pass@N strategy and Direct Preference Optimization (DPO) to improve generation quality; and (3) Difficulty-based dynamic sampling with Group Relative Policy Optimization (GRPO) to mitigate discriminative hallucination. Additionally, post-CoT processing and a cumulative probability-based partitioning method enable efficient online deployment. TaoSR1 significantly outperforms baselines on offline datasets and achieves substantial gains in online side-by-side human evaluations, introducing a novel paradigm for applying CoT reasoning to relevance classification.