Metraipolis › archive › dc_a6bd6d39652d
Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks — arXiv:2611.11714
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11714
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:40:12.327Z
- SHA-256 of the archived text
c2457b115ace55e9f810473bfc9b663e93d06c1328f9d2b3e0463e91435cb9e1- Stable URL of this page
https://metraipolis.com/documento/dc_a6bd6d39652d
How to cite
Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks — arXiv:2611.11714 — arXiv (en), https://arxiv.org/abs/2611.11714 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6bd6d39652d (Metraipolis archive dc_a6bd6d39652d, sha256 c2457b115ace55e9f810473bfc9b663e93d06c1328f9d2b3e0463e91435cb9e1)
BibTeX
@misc{dca6bd6d39652d,
title = {Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks — arXiv:2611.11714},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11714},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6bd6d39652d; sha256 c2457b115ace55e9f810473bfc9b663e93d06c1328f9d2b3e0463e91435cb9e1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11714. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model (LLM) agents increasingly operate in groups, each pursuing an individual objective while jointly determining system performance. If an operator controls which agent observes which other agent, but not their payoffs or messages, how should observations be structured to raise collective welfare? We make the information network (who observes whom) a design object, decoupled from the fixed interaction network over which agents act. Ten identical LLM agents play repeated group-decision games; by default each observes only an anonymous summary of the group's previous-round outcome, and a manager with a fixed budget adds directed observation links that reveal peers' past actions. Across 1,080 episodes and six games spanning coordination, anti-coordination, social dilemmas, and discovery, we ask how much information to share and, at a fixed budget, who should observe whom. Disclosure creates behavioral coupling: observation acts as a contagion channel whose welfare effect depends on the alignment between individually attractive behavior and the collective objective. First, the value of information is alignment-contingent: more peer information tends to help or be neutral when individual behavior is aligned with the collective goal, but under free-riding or congestion externalities it amplifies collectively harmful behavior; in a public-goods game the group does best with no information at all. We read this sign separation as a cross-game regularity within one controlled LLM population, not a model-invariant law. Second, at a fixed budget, who observes whom matters primarily when coupling is harmful: a modular "barbell" that lets sub-populations entrench harmful behavior is reliably the worst wiring, reversing the network-reciprocity intuition from human evolutionary game theory. These results argue against a default of full transparency for agent collectives. 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); Computer Science and Game Theory (cs.GT); Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2611.11714 — 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 2026-11-10T18:37:22.453Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).