# Generative Reasoning Recommendation via LLMs

arXiv: https://arxiv.org/abs/2510.20815 · HTML: https://mlsanity.com/paper/2510.20815/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [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)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models](https://mlsanity.com/paper/2508.10751/) (2025)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [Reinforced Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2505.19092/) (2025)
- [Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning](https://mlsanity.com/paper/2503.24289/) (2025)
- [QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou](https://mlsanity.com/paper/2411.11739/) (2024)
- [OneRec Technical Report](https://mlsanity.com/paper/2506.13695/) (2025)
- [APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization](https://mlsanity.com/paper/2506.21655/) (2025)
- [VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning](https://mlsanity.com/paper/2507.02626/) (2025)
- [Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation](https://mlsanity.com/paper/2409.07276/) (2024)
- [LLM-CoT Enhanced Graph Neural Recommendation with Harmonized Group Policy Optimization](https://mlsanity.com/paper/2505.12396/) (2025)
- [LLM-I: LLMs are Naturally Interleaved Multimodal Creators](https://mlsanity.com/paper/2509.13642/) (2025)
- [Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval](https://mlsanity.com/paper/2506.14445/) (2025)
- [Bridging Search and Recommendation through Latent Cross Reasoning](https://mlsanity.com/paper/2508.04152/) (2025)
- [RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation](https://mlsanity.com/paper/2509.03131/) (2025)

## Built on by (most cited first, 5 of 5)

- [Dissecting Failure Dynamics in Large Language Model Reasoning](https://mlsanity.com/paper/2604.14528/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation](https://mlsanity.com/paper/2605.10207/) (2026)
- [Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model](https://mlsanity.com/paper/2604.14051/) (2026)
- [The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness](https://mlsanity.com/paper/2608.23154/) (2026)

## Abstract (arXiv)

Despite their remarkable reasoning capabilities across diverse domains, large language models (LLMs) face fundamental challenges in natively functioning as generative reasoning recommendation models (GRRMs), where the intrinsic modeling gap between textual semantics and collaborative filtering signals, combined with the sparsity and stochasticity of user feedback, presents significant obstacles. This work explores how to build GRRMs by adapting pre-trained LLMs, which achieves a unified understanding-reasoning-prediction manner for recommendation tasks. We propose GREAM, an end-to-end framework that integrates three components: (i) Collaborative-Semantic Alignment, which fuses heterogeneous textual evidence to construct semantically consistent, discrete item indices and auxiliary alignment tasks that ground linguistic representations in interaction semantics; (ii) Reasoning Curriculum Activation, which builds a synthetic dataset with explicit Chain-of-Thought supervision and a curriculum that progresses through behavioral evidence extraction, latent preference modeling, intent inference, recommendation formulation, and denoised sequence rewriting; and (iii) Sparse-Regularized Group Policy Optimization (SRPO), which stabilizes post-training via Residual-Sensitive Verifiable Reward and Bonus-Calibrated Group Advantage Estimation, enabling end-to-end optimization under verifiable signals despite sparse successes. GREAM natively supports two complementary inference modes: Direct Sequence Recommendation for high-throughput, low-latency deployment, and Sequential Reasoning Recommendation that first emits an interpretable reasoning chain for causal transparency. Experiments on three datasets demonstrate consistent gains over strong baselines, providing a practical path toward verifiable-RL-driven LLM recommenders.