PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features

Lingyao Li, Haolun Wu, Zhenkun Li, Jiabei Hu, Yu Wang, Xiaoshan Huang, Wenyue Hua, Wenqian Wang

Keywords: Multi-agent Systems, Large Language Models, Business Partner Selection

Abstract:

High-dimensional decision-making tasks, such as business partner selection, involve evaluating large candidate pools with heterogeneous numerical, categorical, and textual features. While large language models (LLMs) offer strong in-context reasoning capabilities, single-agent or debate-style systems often struggle with scalability and consistency in such settings. We propose \name, a hierarchical multi-agent framework that decomposes evaluation into three layers: a Planner Agent that designs strategies, Specialized Agents that perform role-specific assessments, and a Supervisor Agent that integrates their outputs. To support systematic evaluation, we also introduce a curated benchmark dataset of venture capital co-investments, featuring diverse firm attributes and ground-truth syndicates. Across 140 cases, \name consistently outperforms single-agent and debate-based multi-agent baselines, achieving up to 10–15\% higher match rates. Analysis of agent reasoning shows that planners are most responsive to domain-informed prompts, specialists produce complementary feature coverage, and supervisors play an important role in aggregation. Our findings demonstrate that structured collaboration among LLM agents can generate more robust outcomes than scaling individual models, highlighting \name as a promising framework for high-dimensional decision-making in data-rich domains.
Our implementation is available at https://anonymous.4open.science/r/Partner-MAS-7DCE.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 2508