# TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation

arXiv: https://arxiv.org/abs/2508.15388 · HTML: https://mlsanity.com/paper/2508.15388/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models](https://mlsanity.com/paper/2306.10933/) (2023)
- [Text-like Encoding of Collaborative Information in Large Language Models for Recommendation](https://mlsanity.com/paper/2406.03210/) (2024)
- [Aligning Large Language Models for Controllable Recommendations](https://mlsanity.com/paper/2403.05063/) (2024)
- [R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems](https://mlsanity.com/paper/2507.17249/) (2025)
- [RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs](https://mlsanity.com/paper/2409.04421/) (2024)
- [Finetuning Large Language Model for Personalized Ranking](https://mlsanity.com/paper/2405.16127/) (2024)

## Built on by (most cited first, 7 of 7)

- [Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning](https://mlsanity.com/paper/2603.07972/) (2026)
- [Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation](https://mlsanity.com/paper/2512.01372/) (2025)
- [RaMem: Contextual Reinstatement for Long-term Agentic Memory](https://mlsanity.com/paper/2606.22844/) (2026)
- [SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation](https://mlsanity.com/paper/2511.19514/) (2025)
- [De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models](https://mlsanity.com/paper/2602.03097/) (2026)
- [Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation](https://mlsanity.com/paper/2606.03866/) (2026)
- [TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation](https://mlsanity.com/paper/2604.26247/) (2026)

## Abstract (arXiv)

The extensive world knowledge and powerful reasoning capabilities of large language models (LLMs) have attracted significant attention in recommendation systems (RS). Specifically, The chain of thought (CoT) has been shown to improve the performance of LLMs on complex reasoning tasks for RS. However, due to the fact that LLMs often suffer from hallucination issues, there is no guarantee that their reasoning CoT is effective. A key challenge is to further enhance the recommendation capabilities of LLMs through effective CoT reasonings. Therefore, we propose TrackRec, a framework designed to enhance reasoning capabilities of LLMs for RS. TrackRec specifically focuses on accurately inferring recommendation CoT (RecCoT) for user preference using the knowledge from LLMs. This RecCoT can serve both as an explanation for the LLM's completion of recommendation tasks and as auxiliary features to assist recommendation models in accomplishing recommendation tasks. TrackRec consists of a RecCoT generator (G) and a RecCoT validator (V). Furthermore, we design alternating feedback learning mechanism that G undergoes direct preference optimization via feedback from V to produce increasingly accurate RecCoT aligned with V's standards. Meanwhile, V is fine-tuned using the inference feedback from G to enhance its validation capabilities in alignment with recommendation tasks. Through iterative alternating feedback learning between G and V, TrackRec continuously improves the user preference analysis capability of G and the validation capacity of V. Extensive experiments demonstrate the effectiveness of our approach, showing that it surpasses state-of-the-art methods. Moreover, TrackRec has been deployed on a lagre advertising platform with hundreds of millions of users, achieving substantial gains.