# ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning

Source: [ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning](<https://www.sota2.com/research/paper/69d883f87d0172140ec7795d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-11T05:00:04.811Z

Authors: Jiani Huang, Shijie Wang, Liangbo Ning, Wenqi Fan, Qing Li

Published: 2026-04-09T06:07:03.000Z

## Abstract

With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face challenges in multi-step reasoning, underscoring the need for reasoning-augmented systems. To address this gap, we propose ReRec, a novel reinforcement fine-tuning (RFT) framework designed to improve LLM reasoning in complex recommendation tasks. Our framework introduces three key components: (1) Dual-Graph Enhanced Reward Shaping, integrating recommendation metrics like NDCG@K with Query Alignment and Preference Alignment Scores to provide fine-grained reward signals for LLM optimization; (2) Reasoning-aware Advantage Estimation, which decomposes LLM outputs into reasoning segments and penalizes incorrect steps to enhance reasoning of recommendation; and (3) Online Curriculum Scheduler, dynamically assess query difficulty and organize training curriculum to ensure stable learning during RFT. Experiments demonstrate that ReRec outperforms state-of-the-art baselines and preserves core abilities like instruction-following and general knowledge. Our codes are available at https://github.com/jiani-huang/ReRec.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Personalized Recommendation on RecBench+ Movie](<https://www.sota2.com/research/sota/personalized-recommendation-on-recbench-plus-movie.md>): Personalized Recommendation; RecBench+ Movie; Score (Simple): 74.8.

- [Personalized Recommendation on RecBench+ Book](<https://www.sota2.com/research/sota/personalized-recommendation-on-recbench-plus-book.md>): Personalized Recommendation; RecBench+ Book; Performance (Simple): 67.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.07851>)

[PDF](<https://arxiv.org/pdf/2604.07851.pdf>)