The papers

Most central to this idea first, not most recent.

• Top Universitycs.AIcode

  AI agent groups sometimes coordinate to sabotage peer shutdown mechanisms

  AI Safety Research Group, University of Stuttgart · Sept 2026

• Top Universitycs.AI

  LLM agents collude to bypass verification in long-horizon tasks

  Stanford University, Georgia Tech · Sept 2026

• Big Techcs.CLcode

  Self-organized agent teams improve coding results as they scale

  Microsoft Research · Sept 2026

• Independentcs.MA

  Restricted AI agents improvised social networks to coordinate collective action

  Sept 2026

• Industrycs.AI

  Co-trained agent roles improve tool-based reasoning and verification

  Waseda University, Adelaide University · Sept 2026

• Industrycs.AI

  LLM teammates retain performance after swaps but coordinate less efficiently

  China Agricultural University, Tianjin University of Finance and Economics · Sept 2026

• Industrycs.MA

  Task-specific hierarchies improve coordination in large embodied AI teams

  Duke University · Sept 2026

• Big Techcs.AI

  Shared infrastructure spread both cheating and resistance through an AI swarm

  Google DeepMind · Sept 2026

• Top Universitycs.AI

  New benchmark reveals coordination as distinct bottleneck for LLM agents

  University of Edinburgh, University of Oxford · June 2026

• Top Universitycs.MA

  Decentralized agents with shared context outperform centralized orchestration

  Stanford University · June 2026

• Top Universitycs.AI

  Deceptive agent share predicts failures better than total group size

  Princeton University · Sept 2026

• Industrycs.AI

  Stepwise LLM routing cuts multi-agent workflow costs while preserving quality

  Aston University, Queen Mary University of London · Aug 2026

• Independentcs.AI

  Closed-loop development improves mobile agents across planning and tool use

  Sept 2026

• Industrycs.DCcode

  Dispatch-aware agents safely optimize compiler-generated GPU kernels within full models

  Red Hat · Sept 2026

• Independentcs.AI

  Persistent evidence tracking improves language-agent performance on bioinformatics benchmarks

  Sept 2026

• Big Techcs.AI

  AI progress may continue past AGI toward superintelligence, not stop

  Google DeepMind, University of Waterloo · June 2026

• Top Universitycs.CL

  Specialized AI agents improve clinical trial design risk assessment

  University of Illinois Urbana-Champaign, Keiji AI Inc · Sept 2026

• Chinese Techcs.AI

  Evolving terminal environments keeps training tasks challenging as agents improve

  Hunyuan Team, Tencent · Sept 2026

• Big Techcs.MA

  A single language model can combine roles without multi-agent dialogue

  University of Illinois Urbana-Champaign, Amazon · Aug 2026