# SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation

arXiv: https://arxiv.org/abs/2601.21452 · HTML: https://mlsanity.com/paper/2601.21452/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization](https://mlsanity.com/paper/2008.07873/) (2020)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Reinforcement learning based recommender systems: A survey](https://mlsanity.com/paper/2101.06286/) (2021)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [GenRec: Large Language Model for Generative Recommendation](https://mlsanity.com/paper/2307.00457/) (2023)
- [LLaRA: Large Language-Recommendation Assistant](https://mlsanity.com/paper/2312.02445/) (2023)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System](https://mlsanity.com/paper/2404.11343/) (2024)
- [BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping](https://mlsanity.com/paper/2510.18927/) (2025)

## Built on by (most cited first, 1 of 1)

- [ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation](https://mlsanity.com/paper/2604.22169/) (2026)

## Abstract (arXiv)

Reinforcement learning-based preference optimization is increasingly used to align list-wise generative recommenders with complex, multi-objective user feedback, yet existing optimizers such as Gradient-Bounded Policy Optimization (GBPO) exhibit structural limitations in recommendation settings. We identify a Symmetric Conservatism failure mode in which symmetric update bounds suppress learning from rare positive signals (e.g., cold-start items), static negative-sample constraints fail to prevent diversity collapse under rejection-dominated feedback, and group-normalized multi-objective rewards lead to low-resolution training signals. To address these issues, we propose SAGE (Sequence-level Adaptive Gradient Evolution), a unified optimizer designed for list-wise generative recommendation. SAGE introduces sequence-level signal alignment via a geometric-mean importance ratio and a decoupled multi-objective advantage estimator to reduce token-level variance and mitigate reward collapse, together with asymmetric adaptive bounding that applies positive Boost updates to successful slates and an entropy-aware penalty to discourage low-diversity failures. Experiments on Amazon Product Reviews and the large-scale RecIF-Bench demonstrate consistent improvements in top-K accuracy, cold-start recall, and diversity across both Semantic-ID and native-text action spaces, while preserving numerical stability during training. These results suggest that asymmetric, sequence-aware policy optimization provides a principled and effective framework for addressing optimization failures in generative recommendation.