# Multi-User Large Language Model Agents

arXiv: https://arxiv.org/abs/2604.08567 · HTML: https://mlsanity.com/paper/2604.08567/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control](https://mlsanity.com/paper/2505.18279/) (2025)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Generative Social Choice](https://mlsanity.com/paper/2309.01291/) (2023)
- [Multi-Agent Coordination across Diverse Applications: A Survey](https://mlsanity.com/paper/2502.14743/) (2025)
- [A Closer Look at System Prompt Robustness](https://mlsanity.com/paper/2502.12197/) (2025)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [Multi-Principal Assistance Games](https://mlsanity.com/paper/2007.09540/) (2020)
- [JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model](https://mlsanity.com/paper/2504.03770/) (2025)
- [Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs](https://mlsanity.com/paper/2510.05154/) (2025)
- [ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning via Tool-integrated Action for Dynamic Offer Optimization](https://mlsanity.com/paper/2503.07129/) (2025)
- [Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations](https://mlsanity.com/paper/2405.20195/) (2024)

## Built on by (most cited first, 7 of 7)

- [One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL](https://mlsanity.com/paper/2608.12253/) (2026)
- [Personalizing LLM Agent Memory Using Biometrics](https://mlsanity.com/paper/2609.08558/) (2026)
- [Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work](https://mlsanity.com/paper/2609.29901/) (2026)
- [Org-Agent: Beyond Personal Assistants Towards Organizational Agents](https://mlsanity.com/paper/2609.34392/) (2026)
- [Audience-Bound Persistent Memory: Authorization Across the Memory Lifecycle](https://mlsanity.com/paper/2609.36373/) (2026)
- [Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams](https://mlsanity.com/paper/2610.00583/) (2026)
- [Workerville: Towards an Organizational Behavior Account of Agent Safety](https://mlsanity.com/paper/2610.11561/) (2026)

## Abstract (arXiv)

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.