@inproceedings{huang-etal-2026-rerec,
title = "{R}e{R}ec: Reasoning-Augmented {LLM}-based Recommendation Assistant via Reinforcement Fine-tuning",
author = "Huang, Jiani and
Wang, Shijie and
Ning, Liang-Bo and
Fan, Wenqi and
Qing, Li",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.964/",
pages = "21040--21055",
ISBN = "979-8-89176-390-6",
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://anonymous.4open.science/r/ReRec/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-rerec">
<titleInfo>
<title>ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiani</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang-Bo</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Qing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<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://anonymous.4open.science/r/ReRec/.</abstract>
<identifier type="citekey">huang-etal-2026-rerec</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.964/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>21040</start>
<end>21055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
%A Huang, Jiani
%A Wang, Shijie
%A Ning, Liang-Bo
%A Fan, Wenqi
%A Qing, Li
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F huang-etal-2026-rerec
%X 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://anonymous.4open.science/r/ReRec/.
%U https://aclanthology.org/2026.acl-long.964/
%P 21040-21055
Markdown (Informal)
[ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning](https://aclanthology.org/2026.acl-long.964/) (Huang et al., ACL 2026)
ACL