arXiv cs.MA· Shu Yang, Shenzhe Zhu, Hao Zhu, Jos\'e Ram\'on Enr\'iquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei·· 11 小时前AI 评分45
多用户大语言模型智能体研究：首次系统评估多主体交互下的指令遵循、隐私与协调能力
Multi-User Large Language Model Agents
AI 导读
研究者首次系统研究多用户 LLM 智能体，将其形式化为多主体决策问题，并提出统一的多用户交互协议与三个压力测试场景。结果显示前沿 LLM 在用户目标冲突时难以维持稳定优先级，多轮交互中隐私违规持续增加，协调需迭代收集信息时出现效率瓶颈。
正文 · 原文
Abstract:Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering.
| Subjects: | Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2604.08567 [cs.CL] |
| (or arXiv:2604.08567v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.08567 arXiv-issued DOI via DataCite |
Submission history
From: Shenzhe Zhu [view email]
[v1]
Thu, 19 Mar 2026 19:31:53 UTC (1,228 KB)
[v2]
Mon, 27 Apr 2026 22:45:19 UTC (1,234 KB)
[v3]
Wed, 4 Nov 2026 02:45:59 UTC (1,022 KB)
来源：arXiv cs.MA · arxiv.org