# OneRec-Think: In-Text Reasoning for Generative Recommendation

arXiv: https://arxiv.org/abs/2510.11639 · HTML: https://mlsanity.com/paper/2510.11639/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

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

## Builds on (most cited first, 6 of 6)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2504.13914/) (2025)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [Leveraging LLM Reasoning Enhances Personalized Recommender Systems](https://mlsanity.com/paper/2408.00802/) (2024)
- [RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning](https://mlsanity.com/paper/2502.06101/) (2025)

## Built on by (most cited first, 30 of 51)

- [Reasoning over Semantic IDs Enhances Generative Recommendation](https://mlsanity.com/paper/2603.23183/) (2026)
- [GR2: Generative Reasoning Re-ranker](https://mlsanity.com/paper/2602.07774/) (2026)
- [Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation](https://mlsanity.com/paper/2602.16587/) (2026)
- [RecGPT-V2 Technical Report](https://mlsanity.com/paper/2512.14503/) (2025)
- [OneReason Technical Report](https://mlsanity.com/paper/2606.06260/) (2026)
- [S2GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation](https://mlsanity.com/paper/2601.18664/) (2026)
- [Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators](https://mlsanity.com/paper/2602.22647/) (2026)
- [CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation](https://mlsanity.com/paper/2604.05113/) (2026)
- [Implicit Reasoning for Large Language Model-based Generative Recommendation](https://mlsanity.com/paper/2606.14142/) (2026)
- [Factorized Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2604.26760/) (2026)
- [RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference](https://mlsanity.com/paper/2601.01712/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation](https://mlsanity.com/paper/2605.17648/) (2026)
- [LLMs Need Encoders for Semantic IDs Too](https://mlsanity.com/paper/2606.00324/) (2026)
- [TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation](https://mlsanity.com/paper/2606.07688/) (2026)
- [HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation](https://mlsanity.com/paper/2606.15331/) (2026)
- [HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent](https://mlsanity.com/paper/2512.24787/) (2025)
- [TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems](https://mlsanity.com/paper/2606.25147/) (2026)
- [Think2Go: Generative Next POI Recommendation with LLM Reasoning](https://mlsanity.com/paper/2607.28997/) (2026)
- [Difficulty-Aware Semantic-ID Optimization for Generative Recommendation](https://mlsanity.com/paper/2608.20611/) (2026)
- [Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations](https://mlsanity.com/paper/2609.12270/) (2026)
- [Principled Synthetic Data Enables the First Scaling Laws for LLMs in Recommendation](https://mlsanity.com/paper/2602.07298/) (2026)
- [Awakening Dormant Users: Generative Recommendation with Counterfactual Functional Role Reasoning](https://mlsanity.com/paper/2602.13134/) (2026)
- [AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation](https://mlsanity.com/paper/2603.19710/) (2026)
- [AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimization](https://mlsanity.com/paper/2603.21613/) (2026)
- [Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model](https://mlsanity.com/paper/2604.14051/) (2026)
- [ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation](https://mlsanity.com/paper/2604.22169/) (2026)
- [Learning Evidence Highlighting for Frozen LLMs](https://mlsanity.com/paper/2604.22565/) (2026)
- [Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation](https://mlsanity.com/paper/2605.07613/) (2026)
- [Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study](https://mlsanity.com/paper/2605.22358/) (2026)

## Abstract (arXiv)

The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for explicit and controllable reasoning-a key advantage of LLMs. To bridge this gap, we propose OneRec-Think, a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation. OneRec-Think incorporates: (1) Itemic Alignment: cross-modal Item-Textual Alignment for semantic grounding; (2) Reasoning Activation: Reasoning Scaffolding to activate LLM reasoning within the recommendation context; and (3) Reasoning Enhancement, where we design a recommendation-specific reward function that accounts for the multi-validity nature of user preferences. Experiments across public benchmarks show state-of-the-art performance. Moreover, our proposed "Think-Ahead" architecture enables effective industrial deployment on Kuaishou, achieving a 0.159% gain in APP Stay Time and validating the practical efficacy of the model's explicit reasoning capability.