cs.MANov 17, 2026

Groups of AI agents underuse resources despite shared evidence of increased capacity

Authors: Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari

Organizations: Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8904, Japan · Department of Aeronautics and Astronautics, School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

Abstract

When AI agents share limited resources, such as computing services or public infrastructure, their individual choices affect how much work they complete as a group. Can sharing evidence of what is available let a group make full use of its resources after capacity changes? We tested this with language-model agents choosing between two simulated servers. One server recovered while its status report still listed it as unavailable. Each server had limited capacity per round, so rejected jobs required another attempt before the deadline. Telling agents that recovery was possible reduced missed deadlines. In controlled tests with Anthropic's Claude Haiku 5.5, no agent tried the recovered server after a rule reminder, yet all chose it when shown a successful request record. After sharing, all five models tested left capacity unused. Keeping the success record fixed, we gave agents numbers without instructions, using each value equally often but giving group members either identical or distinct numbers. With OpenAI's GPT-6.1 Sol or Google's Gemini 3.5 Flash-Lite, distinct numbers spread simultaneous requests across servers and increased job completions even though overall choice frequencies barely changed. Telling AI agents which resources are available leaves a second design challenge: helping them spread demand across those resources.

Figures & tables

Explore similar work

CardsList
  1. Warned alike, AI agents avoid the less-crowded road while people take it

    Sep 25, 2026Takahiro Ezaki, Naoto Imura, Katsuhiro NishinariCongestion GamesMulti-Agent Coordination

  2. Increasing intelligence in AI agents can worsen collective outcomes

    Mar 12, 2026Neil F. JohnsonMulti-Agent Resource AllocationMulti-Agent Coordination

  3. Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics

    Sep 17, 2026Wonmi Choi, Minuk Park, Zhixiong Niu +3LLM Inference EfficiencyLLM Agent Workflow Optimization