mlsanityData to 7 Oct 2026

AI Organizations are More Effective but Less Aligned than Individual Agents

arXiv 2604.10290 ↗First posted 11 Apr 2026cs.AIcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 97 references that are in the map. First posted on arXiv 11 Apr 2026.

Builds on

25 of 97 references.

References · 25

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  3. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  5. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  6. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  7. 2022Red Teaming Language Models with Language Modelscited by 983
  8. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  9. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  10. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  11. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  12. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
13 more
  1. 2024Self-Preference Bias in LLM-as-a-Judgecited by 248
  2. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  3. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  4. 2025Multi-Agent Risks from Advanced AIcited by 150
  5. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  6. 2024Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templatescited by 71
  7. 2025OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoningcited by 69
  8. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 58
  9. 2024Adversaries Can Misuse Combinations of Safe Modelscited by 31
  10. 2025Large Language Models Miss the Multi-Agent Markcited by 25
  11. 2025Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analyticscited by 11
  12. 2025Auditing Games for Sandbaggingcited by 10
  13. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systemscited by 5
  2. 2026Copying explains the collective behavior of AI agents in the wildcited by 1
  3. 2026The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Informationcited by 0
  4. 2026Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systemscited by 0