# ThinkRec: Thinking-based recommendation via LLM

arXiv: https://arxiv.org/abs/2505.15091 · HTML: https://mlsanity.com/paper/2505.15091/

## 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 14 of its 51 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [PolyLM: An Open Source Polyglot Large Language Model](https://mlsanity.com/paper/2307.06018/) (2023)
- [GenRec: Large Language Model for Generative Recommendation](https://mlsanity.com/paper/2307.00457/) (2023)
- [Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation](https://mlsanity.com/paper/2503.22675/) (2025)
- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation](https://mlsanity.com/paper/2310.06491/) (2023)
- [Improving LLM-powered Recommendations with Personalized Information](https://mlsanity.com/paper/2502.13845/) (2025)
- [AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback](https://mlsanity.com/paper/2501.13333/) (2025)
- [BTRec: BERT-Based Trajectory Recommendation for Personalized Tours](https://mlsanity.com/paper/2310.19886/) (2023)

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

- [OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System](https://mlsanity.com/paper/2509.18091/) (2025)
- [Reasoning over Semantic IDs Enhances Generative Recommendation](https://mlsanity.com/paper/2603.23183/) (2026)
- [Implicit Reasoning for Large Language Model-based Generative Recommendation](https://mlsanity.com/paper/2606.14142/) (2026)
- [SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation](https://mlsanity.com/paper/2511.19514/) (2025)
- [CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration](https://mlsanity.com/paper/2510.03038/) (2025)
- [RASTP: Representation-Aware Semantic Token Pruning for Generative Recommendation with Semantic Identifiers](https://mlsanity.com/paper/2511.16943/) (2025)
- [MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation](https://mlsanity.com/paper/2601.20234/) (2026)
- [Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation](https://mlsanity.com/paper/2605.07613/) (2026)
- [LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation](https://mlsanity.com/paper/2607.24617/) (2026)
- [From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation](https://mlsanity.com/paper/2608.11493/) (2026)
- [Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders](https://mlsanity.com/paper/2608.20801/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have enabled more semantic-aware recommendations through natural language generation. Existing LLM for recommendation (LLM4Rec) methods mostly operate in a System 1-like manner, relying on superficial features to match similar items based on click history, rather than reasoning through deeper behavioral logic. This often leads to superficial and erroneous recommendations. Motivated by this, we propose ThinkRec, a thinking-based framework that shifts LLM4Rec from System 1 to System 2 (rational system). Technically, ThinkRec introduces a thinking activation mechanism that augments item metadata with keyword summarization and injects synthetic reasoning traces, guiding the model to form interpretable reasoning chains that consist of analyzing interaction histories, identifying user preferences, and making decisions based on target items. On top of this, we propose an instance-wise expert fusion mechanism to reduce the reasoning difficulty. By dynamically assigning weights to expert models based on users' latent features, ThinkRec adapts its reasoning path to individual users, thereby enhancing precision and personalization. Extensive experiments on real-world datasets demonstrate that ThinkRec significantly improves the accuracy and interpretability of recommendations. Our implementations are available at https://github.com/Yu-Qi-hang/ThinkRec.