Multi-User Large Language Model Agents
cs.CL, cs.MA
Submitted: 2026-03-19
Updated: 2026-11-10
Code: https://github.com/Kordi-AI/Multi-User-LLM-Agent
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making…
Terminology
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.
Sources
- GPT-4 Technical Report
- gpt-oss-120b & gpt-oss-20b Model Card
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Multi-Principal Assistance Games
- Generative Social Choice
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Understanding the planning of LLM agents: A survey
- Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
- A Closer Look at System Prompt Robustness
- JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
- Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
- Multi-Agent Coordination across Diverse Applications: A Survey
- Qwen3 Technical Report
- MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
- A-MEM: Agentic Memory for LLM Agents
- Foundation Models for Decision Making: Problems, Methods, and Opportunities
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
- SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
- Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data