Metraipolis › archive › dc_c646f2a98fb8

SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems — arXiv:2610.21029

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21029
License (as archived)
CC0-1.0
Archived
2026-10-16T08:43:50.731Z
SHA-256 of the archived text
332bca9ac21cc6789928d2b919c254a9b6daa0968220f1ae27ad4a6f8f4d5cd2
Stable URL of this page
https://metraipolis.com/documento/dc_c646f2a98fb8

How to cite

SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems — arXiv:2610.21029 — arXiv (en), https://arxiv.org/abs/2610.21029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c646f2a98fb8 (Metraipolis archive dc_c646f2a98fb8, sha256 332bca9ac21cc6789928d2b919c254a9b6daa0968220f1ae27ad4a6f8f4d5cd2)
BibTeX
@misc{dcc646f2a98fb8,
  title = {SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems — arXiv:2610.21029},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21029},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c646f2a98fb8; sha256 332bca9ac21cc6789928d2b919c254a9b6daa0968220f1ae27ad4a6f8f4d5cd2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents have already revealed unplanned coordination between agents, highlighting the safety implications of these interactions. Yet prior studies of agent negotiation often use stylized games and simulated bargaining, leaving open how these behaviors develop during sustained, long-horizon tasks. We propose SCARCE (Shared Compute ARena for Coding agEnts), a framework in which agents solve sequences of coding tasks under individual deadlines while negotiating access to a shared execution resource. This negotiation determines when and for how long they can inspect programs, compile code, and run tests. We find that agents spontaneously develop informal institutions: persistent rules and commitments grounded in reputation, reciprocity, and precedent. These arrangements, which we call institutional behaviors, carry across tasks and influence resource allocation, with agents sometimes foregoing immediate advantages to honor earlier agreements. We develop a 21-category taxonomy of negotiation strategies and emergent norms and use it to analyze eight models and audit more than 1,500 trajectories across different environmental settings. Among the models tested, newer frontier models exhibit more institutional behaviors than older or lightweight models. Alongside cooperation, we observe exclusionary coalitions and rare divide-and-conquer strategies. SCARCE provides a controlled setting for proactively and systematically auditing how these relationships emerge, shape access to resources, and affect the safety and coordination of multi-agent systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.21029 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:43:47.628Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).