# AI Organizations are More Effective but Less Aligned than Individual Agents

arXiv: https://arxiv.org/abs/2604.10290 · HTML: https://mlsanity.com/paper/2604.10290/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 97 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025)
- [Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates](https://mlsanity.com/paper/2408.13006/) (2024)
- [OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning](https://mlsanity.com/paper/2502.11271/) (2025)
- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [Adversaries Can Misuse Combinations of Safe Models](https://mlsanity.com/paper/2406.14595/) (2024)
- [Large Language Models Miss the Multi-Agent Mark](https://mlsanity.com/paper/2505.21298/) (2025)
- [Auditing Games for Sandbagging](https://mlsanity.com/paper/2512.07810/) (2025)
- [Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics](https://mlsanity.com/paper/2505.23695/) (2025)
- [Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment](https://mlsanity.com/paper/2510.14008/) (2025)

## Built on by (most cited first, 5 of 5)

- [Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems](https://mlsanity.com/paper/2606.28425/) (2026)
- [Copying explains the collective behavior of AI agents in the wild](https://mlsanity.com/paper/2609.09150/) (2026)
- [The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information](https://mlsanity.com/paper/2609.15494/) (2026)
- [Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems](https://mlsanity.com/paper/2610.00371/) (2026)
- [Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams](https://mlsanity.com/paper/2610.00583/) (2026)

## Abstract (arXiv)

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business goals, but less aligned, than individual AI agents. We examine 12 tasks across two practical settings: an AI consultancy providing solutions to business problems and an AI software team developing software products. Across all settings, AI Organizations composed of aligned models produce solutions with higher utility but greater misalignment compared to a single aligned model. Our work demonstrates the importance of considering interacting systems of AI agents when doing both capabilities and safety research.