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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Jiani, Wang, Shijie, Ning, Liangbo, Fan, Wenqi, Li, Qing
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917394681692160
author Huang, Jiani
Wang, Shijie
Ning, Liangbo
Fan, Wenqi
Li, Qing
author_facet Huang, Jiani
Wang, Shijie
Ning, Liangbo
Fan, Wenqi
Li, Qing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07851
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
Huang, Jiani
Wang, Shijie
Ning, Liangbo
Fan, Wenqi
Li, Qing
Information Retrieval
Artificial Intelligence
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.
title ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.07851