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

arXiv: https://arxiv.org/abs/2603.19909 · HTML: https://mlsanity.com/paper/2603.19909/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 60 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 15 of 15)

- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling](https://mlsanity.com/paper/2407.09887/) (2024)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- [GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation](https://mlsanity.com/paper/2006.03736/) (2020)
- [A General Optimization Technique for High Quality Community Detection in Complex Networks](https://mlsanity.com/paper/1308.3508/) (2013)
- [Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs](https://mlsanity.com/paper/2303.08941/) (2023)
- [Thinking inside The Box: Learning Hypercube Representations for Group Recommendation](https://mlsanity.com/paper/2204.02592/) (2022)
- [ConsRec: Learning Consensus Behind Interactions for Group Recommendation](https://mlsanity.com/paper/2302.03555/) (2023)
- [Network Data](https://mlsanity.com/paper/1912.06346/) (2019)
- [Enumerating Fair Packages for Group Recommendations](https://mlsanity.com/paper/2105.14423/) (2021)
- [When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation](https://mlsanity.com/paper/2507.07436/) (2025)
- [ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search](https://mlsanity.com/paper/2504.10893/) (2025)
- [RuleAgent: Discovering Rules for Recommendation Denoising with Autonomous Language Agents](https://mlsanity.com/paper/2503.23374/) (2025)

## Abstract (arXiv)

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.