多使用者大型語言模型代理

摘要

大型語言模型（LLM）及基於LLM的智能體正日益作為規劃與決策輔助工具被部署，然而現有系統大多隱性優化於單一主體的互動模式——模型被設計為滿足單一主導用戶的目標，其指令被視為權威與效用的唯一來源。但隨著這些模型被整合至團隊工作流與組織工具中，它們越來越需要同時服務多個具有不同角色、偏好和權限層級的用戶，從而形成存在不可避免衝突、信息不對稱和隱私約束的多用戶多主體場景。本研究首次對多用戶LLM智能體展開系統性探討：我們先將多用戶與LLM智能體的互動形式化為多主體決策問題，即單一智能體需協調多方用戶可能存在的利益衝突及相關挑戰；接著提出統一的多用戶互動協議，並設計三種針對性壓力測試場景，以評估當前LLM在指令遵循、隱私保護與協調能力方面的表現。實驗結果揭示系統性缺陷：前沿LLM在面對衝突性用戶目標時難以保持穩定的優先級排序，在多輪互動中隱私洩露風險遞增，且當協調需要迭代式信息收集時會出現效率瓶頸。

English

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.

多使用者大型語言模型代理

Multi-User Large Language Model Agents

摘要

Support