AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (3.2 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access | Just Accepted

MERGE:AMemory-Enhanced LLMAgent Framework for Explainable Bundle Recommendation

Yuxuan Li†, Qimeng Niu†, Bowen Hao( ), Tingting Li, Yufan Yang, Chaoran Wang

School of Management, Capital Normal University, Beijing 100048, China

† These authors contributed equally to this work.

Show Author Information

Abstract

Bundle recommendation aims to accurately capture user preferences from the complex interactions among users, bundles, and items to generate explainable recommendations. However, existing methods based on large language models (LLMs) treat user interactions as static text, over-looking the dynamic evolution of user preferences. Although recent memory-augmented LLM approaches such as MR.Rec and MemoCRS maintain external memory, their heuristic update rules are non-adaptive and designed solely for in-dividual recommendation, rendering them unsuitable for bundle recommendation scenarios. To address these issues, we propose MERGE, a Memory-Enhanced LLM Agent that autonomously manages memory in response to evolving user behaviors. Specifically, MERGE consists of a Memory Mod-ule and a Reasoning Module. The Memory Module employs a token-based hash structure to dynamically manage up-to-date user profiles through insert, update, forget, summary, and query operations, all of which are triggered by the current user interactions. The Reasoning Module then performs multi-stage reasoning based on retrieved information to generate explainable recommendations. We train MERGE using reinforcement fine-tuning (RFT), which first applies supervised fine-tuning (SFT) to establish a foundational understanding of the task, followed by group relative policy optimization (GRPO) to enhance its ability to invoke the Memory and Reasoning Modules. Experimental results on two benchmark datasets show that MERGE significantly outperforms existing state-of-the-art methods in both recommendation accuracy and explanation quality. We open-source our model and code at https://huggingface.co/no1forever/MERGE.

References

【1】
【1】
 
 
Tsinghua Science and Technology

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Li Y, Niu Q, Hao B, et al. MERGE:AMemory-Enhanced LLMAgent Framework for Explainable Bundle Recommendation. Tsinghua Science and Technology, 2026, https://doi.org/10.26599/TST.2026.9010103

187

Views

16

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Received: 28 March 2026
Revised: 11 August 2026
Accepted: 11 November 2026
Available online: 16 November 2026

© The author(s) 2026.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).