Research

Paper

AI LLM March 20, 2026

DALI: LLM-Agent Enhanced Dual-Stream Adaptive Leadership Identification for Group Recommendations

Authors

Boxun Song, Min Gao, Jiawei Cheng

Abstract

Group recommendation systems play a pivotal role in supporting collective decisions across various contexts, from leisure activities to organizational team-building. Existing group recommendation approaches typically use either handcrafted aggregation rules (e.g. mean, least misery, weighted sum) or neural aggregation models (e.g. attention-based deep learning frameworks), yet both fall short in distinguishing leader-dominated from collaborative groups and often misrepresent true group preferences, especially when a single member disproportionately influences group choices. To address these limitations, we propose the Dual-stream Adaptive Leadership Identification (DALI) framework, which uniquely combines the symbolic reasoning capabilities of Large Language Models (LLMs) with neural network-based representation learning. Specifically, DALI introduces two key innovations: a dynamic rule generation module that autonomously formulates and evolves identification rules through iterative performance feedback, and a neuro-symbolic aggregation mechanism that concurrently employs symbolic reasoning to robustly recognize leadership groups and attention-based neural aggregation to accurately model collaborative group dynamics. Experiments conducted on the Mafengwo travel dataset confirm that DALI significantly improves recommendation accuracy compared to existing frameworks, highlighting its capability to dynamically adapt to complex, real-world group decision environments.

Metadata

arXiv ID: 2603.19909
Provider: ARXIV
Primary Category: cs.IR
Published: 2026-03-20
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19909v1</id>\n    <title>DALI: LLM-Agent Enhanced Dual-Stream Adaptive Leadership Identification for Group Recommendations</title>\n    <updated>2026-03-20T12:47:17Z</updated>\n    <link href='https://arxiv.org/abs/2603.19909v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19909v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Group recommendation systems play a pivotal role in supporting collective decisions across various contexts, from leisure activities to organizational team-building. Existing group recommendation approaches typically use either handcrafted aggregation rules (e.g. mean, least misery, weighted sum) or neural aggregation models (e.g. attention-based deep learning frameworks), yet both fall short in distinguishing leader-dominated from collaborative groups and often misrepresent true group preferences, especially when a single member disproportionately influences group choices. To address these limitations, we propose the Dual-stream Adaptive Leadership Identification (DALI) framework, which uniquely combines the symbolic reasoning capabilities of Large Language Models (LLMs) with neural network-based representation learning. Specifically, DALI introduces two key innovations: a dynamic rule generation module that autonomously formulates and evolves identification rules through iterative performance feedback, and a neuro-symbolic aggregation mechanism that concurrently employs symbolic reasoning to robustly recognize leadership groups and attention-based neural aggregation to accurately model collaborative group dynamics. Experiments conducted on the Mafengwo travel dataset confirm that DALI significantly improves recommendation accuracy compared to existing frameworks, highlighting its capability to dynamically adapt to complex, real-world group decision environments.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <published>2026-03-20T12:47:17Z</published>\n    <arxiv:comment>under review</arxiv:comment>\n    <arxiv:primary_category term='cs.IR'/>\n    <author>\n      <name>Boxun Song</name>\n    </author>\n    <author>\n      <name>Min Gao</name>\n    </author>\n    <author>\n      <name>Jiawei Cheng</name>\n    </author>\n  </entry>"
}