MERGE:AMemory-Enhanced LLMAgent Framework for Explainable Bundle Recommendation

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.

Authors

Institutions

Publication Details

Journal
Tsinghua Science & Technology
Published
2026-11-16
DOI
https://doi.org/10.26599/tst.2026.9010103
Primary Topic
Recommender Systems and Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MERGE:AMemory-Enhanced LLMAgent Framework for Explainable Bundle Recommendation

Qimeng Niu, Yuxuan Li, Bowen Hao, Chaoran Wang et al.
Tsinghua Science & Technology
Recommender Systems and Techniques
article

MERGE:AMemory-Enhanced LLMAgent Framework for Explainable Bundle Recommendation

Qimeng Niu, Yuxuan Li, Bowen Hao, Chaoran Wang, Yufan Yang, Tingting Li
article en

Abstract

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.

Tsinghua Science & Technology
Capital Normal University (CN)
Capital Normal University, National Natural Science Foundation of China
Recommender Systems and Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon