# LLM reasoning for recommendation

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

## Key facts

- LLM reasoning for recommendation: 163 papers on arXiv since 2022 (data through 14 Oct 2026).
- 19 of its 163 mapped papers (12%) cite “Leveraging LLM Reasoning Enhances Personalized Recommender Systems” (2024, arXiv 2408.00802).
- 19 of its 163 mapped papers (12%) cite “OneRec-Think: In-Text Reasoning for Generative Recommendation” (2025, arXiv 2510.11639).
- 2 new papers 17 Sep–14 Oct.

## Most cited here

- [Leveraging LLM Reasoning Enhances Personalized Recommender Systems](https://mlsanity.com/paper/2408.00802/) (2024), cited by 19 papers here
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025), cited by 19 papers here
- [Reinforced Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2505.19092/) (2025), cited by 18 papers here
- [Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation](https://mlsanity.com/paper/2502.02061/) (2025), cited by 14 papers here
- [Can Small Language Models be Good Reasoners for Sequential Recommendation?](https://mlsanity.com/paper/2403.04260/) (2024), cited by 12 papers here
- [Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation](https://mlsanity.com/paper/2506.05069/) (2025), cited by 12 papers here
- [Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation](https://mlsanity.com/paper/2408.06276/) (2024), cited by 9 papers here
- [ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning](https://mlsanity.com/paper/2410.23180/) (2024), cited by 9 papers here
- [Slow Thinking for Sequential Recommendation](https://mlsanity.com/paper/2504.09627/) (2025), cited by 9 papers here
- [R2ec: Towards Large Recommender Models with Reasoning](https://mlsanity.com/paper/2505.16994/) (2025), cited by 9 papers here

## New (17 Sep–14 Oct)

- [Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation](https://mlsanity.com/paper/2610.02968/) (2026-10-02)
- [KUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative Recommendation](https://mlsanity.com/paper/2609.39828/) (2026-09-30)