# GR2: Generative Reasoning Re-ranker

arXiv: https://arxiv.org/abs/2602.07774 · HTML: https://mlsanity.com/paper/2602.07774/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

## Builds on (most cited first, 30 of 33)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention](https://mlsanity.com/paper/2506.13585/) (2025)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Wukong: Towards a Scaling Law for Large-Scale Recommendation](https://mlsanity.com/paper/2403.02545/) (2024)
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025)
- [Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://mlsanity.com/paper/2404.15676/) (2024)
- [LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations](https://mlsanity.com/paper/2406.12433/) (2024)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [OneRec-V2 Technical Report](https://mlsanity.com/paper/2508.20900/) (2025)
- [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://mlsanity.com/paper/2505.20046/) (2025)
- [MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval](https://mlsanity.com/paper/2506.12364/) (2025)
- [Neural Re-ranking in Multi-stage Recommender Systems: A Review](https://mlsanity.com/paper/2202.06602/) (2022)
- [Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation](https://mlsanity.com/paper/2409.03271/) (2024)
- [R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems](https://mlsanity.com/paper/2507.17249/) (2025)
- [OpenOneRec Technical Report](https://mlsanity.com/paper/2512.24762/) (2025)
- [External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation](https://mlsanity.com/paper/2502.17494/) (2025)
- [360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation](https://mlsanity.com/paper/2501.16450/) (2025)
- [The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit](https://mlsanity.com/paper/2501.02173/) (2025)

## Built on by (most cited first, 11 of 11)

- [ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation](https://mlsanity.com/paper/2606.28357/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [Learning Evidence Highlighting for Frozen LLMs](https://mlsanity.com/paper/2604.22565/) (2026)
- [Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation](https://mlsanity.com/paper/2606.27732/) (2026)
- [End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference](https://mlsanity.com/paper/2606.27743/) (2026)
- [GR2 Technical Report](https://mlsanity.com/paper/2606.31984/) (2026)
- [Diffusion-GR2: Diffusion Generative Reasoning Re-ranker](https://mlsanity.com/paper/2607.01170/) (2026)
- [SCOReD: Student-Aware CoT Optimization for Recommendation Distillation](https://mlsanity.com/paper/2607.05734/) (2026)
- [An LLM-powered Agentic Recommendation System for Connected TV Content Discovery](https://mlsanity.com/paper/2607.09988/) (2026)
- [DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification](https://mlsanity.com/paper/2607.25069/) (2026)
- [The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness](https://mlsanity.com/paper/2608.23154/) (2026)

## Abstract (arXiv)

Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on retrieval and ranking, while the reranking phase, critical for refining final recommendations, is largely overlooked; (2) LLMs are typically used in zero-shot or supervised fine-tuning settings, leaving their reasoning abilities, especially those enhanced through reinforcement learning (RL) and high-quality reasoning data, underexploited; (3) items are commonly represented by non-semantic IDs, creating major scalability challenges in industrial systems with billions of identifiers. To address these gaps, we propose the Generative Reasoning Reranker (GR2), an end-to-end framework with a three-stage training pipeline tailored for reranking. First, a pretrained LLM is mid-trained on semantic IDs encoded from non-semantic IDs via a tokenizer achieving ≥99% uniqueness. Next, a stronger larger-scale LLM generates high-quality reasoning traces through carefully designed prompting and rejection sampling, which are used for supervised fine-tuning to impart foundational reasoning skills. Finally, we apply Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO), enabling scalable RL supervision with verifiable rewards designed specifically for reranking. Experiments on two real-world datasets demonstrate GR2's effectiveness: it surpasses the state-of-the-art OneRec-Think by 2.4% in Recall@5 and 1.3% in NDCG@5. Ablations confirm that advanced reasoning traces yield substantial gains across metrics. We further find that RL reward design is crucial in reranking: LLMs tend to exploit reward hacking by preserving item order, motivating conditional verifiable rewards to mitigate this behavior and optimize reranking performance.