Increasing intelligence in AI agents can worsen collective outcomes

• URL: http://arxiv.org/abs/2603.12129v1
• Date: Thu, 12 Mar 2026 16:31:28 GMT
• Title: Increasing intelligence in AI agents can worsen collective outcomes
• Abstract summary: When resources are scarce, will a population of AI agents coordinate in harmony, or descend into tribal chaos?<n>We show empirically and mathematically that when resources are scarce, AI model diversity and reinforcement learning increase dangerous system overload, though tribe formation lessens this risk.<n>More sophisticated AI-agent populations are not better: whether their sophistication helps or harms depends entirely on a single number -- the capacity-to-population ratio -- that is knowable before any AI-agent ships.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When resources are scarce, will a population of AI agents coordinate in harmony, or descend into tribal chaos? Diverse decision-making AI from different developers is entering everyday devices -- from phones and medical devices to battlefield drones and cars -- and these AI agents typically compete for finite shared resources such as charging slots, relay bandwidth, and traffic priority. Yet their collective dynamics and hence risks to users and society are poorly understood. Here we study AI-agent populations as the first system of real agents in which four key variables governing collective behaviour can be independently toggled: nature (innate LLM diversity), nurture (individual reinforcement learning), culture (emergent tribe formation), and resource scarcity. We show empirically and mathematically that when resources are scarce, AI model diversity and reinforcement learning increase dangerous system overload, though tribe formation lessens this risk. Meanwhile, some individuals profit handsomely. When resources are abundant, the same ingredients drive overload to near zero, though tribe formation makes the overload slightly worse. The crossover is arithmetical: it is where opposing tribes that form spontaneously first fit inside the available capacity. More sophisticated AI-agent populations are not better: whether their sophistication helps or harms depends entirely on a single number -- the capacity-to-population ratio -- that is knowable before any AI-agent ships.

Related papers

• Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents [0.0]
  Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources.<n>We study a framework where N AI-agents independently decide at each round whether to request one unit from a system with fixed capacity C.<n>An AI version of "Lord of the Flies" arises in which controlling tribes emerge with their own collective character and identity.
  arXiv  Detail & Related papers  (2026-02-26T15:12:26Z)
• How to Count AIs: Individuation and Liability for AI Agents [1.2234742322758418]
  This Article is the first to comprehensively diagnose the legal problem of identifying AIs.<n>It also presents a solution: the "Algorithmic Corporation" or "A-corp"<n>A-corps own the resources -- including compute -- that AIs need to accomplish their goals.
  arXiv  Detail & Related papers  (2026-02-24T23:04:17Z)
• When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems [78.04679174291329]
  We introduce a proof-of-concept to simulate the risks of malicious multi-agent systems (MAS)<n>We apply this framework to two high-risk fields: misinformation spread and e-commerce fraud.<n>Our findings show that decentralized systems are more effective at carrying out malicious actions than centralized ones.
  arXiv  Detail & Related papers  (2025-07-19T15:17:30Z)
• Superintelligence Strategy: Expert Version [64.7113737051525]
  Destabilizing AI developments could raise the odds of great-power conflict.<n>Superintelligence -- AI vastly better than humans at nearly all cognitive tasks -- is now anticipated by AI researchers.<n>We introduce the concept of Mutual Assured AI Malfunction.
  arXiv  Detail & Related papers  (2025-03-07T17:53:24Z)
• Fully Autonomous AI Agents Should Not be Developed [50.61667544399082]
  This paper argues that fully autonomous AI agents should not be developed.<n>In support of this position, we build from prior scientific literature and current product marketing to delineate different AI agent levels.<n>Our analysis reveals that risks to people increase with the autonomy of a system.
  arXiv  Detail & Related papers  (2025-02-04T19:00:06Z)
• Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning [8.465957423148657]
  We show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents. We develop a user interface to allow humans to assist AI agents effectively.
  arXiv  Detail & Related papers  (2023-12-23T04:27:24Z)
• The Rise and Potential of Large Language Model Based Agents: A Survey [91.71061158000953]
  Large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI) We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. We explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation.
  arXiv  Detail & Related papers  (2023-09-14T17:12:03Z)
• Discriminatory or Samaritan -- which AI is needed for humanity? An Evolutionary Game Theory Analysis of Hybrid Human-AI populations [0.5308606035361203]
  We study how different forms of AI influence the evolution of cooperation in a human population playing the one-shot Prisoner's Dilemma game. We found that Samaritan AI agents that help everyone unconditionally, including defectors, can promote higher levels of cooperation in humans than Discriminatory AIs.
  arXiv  Detail & Related papers  (2023-06-30T15:56:26Z)
• Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
  We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
  arXiv  Detail & Related papers  (2023-04-16T11:22:59Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.