Metraipolis › archive › dc_d102d43cbe27
Flag Game: A Toy Model for Mechanistic Swarm Interpretability — arXiv:2609.19124
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19124
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T17:54:19.368Z
- SHA-256 of the archived text
0ac31d3e01d487da1cba1e92f92fed70fd0204ca47f544ddd8dbb50b3161414c- Stable URL of this page
https://metraipolis.com/documento/dc_d102d43cbe27
How to cite
Flag Game: A Toy Model for Mechanistic Swarm Interpretability — arXiv:2609.19124 — arXiv (en), https://arxiv.org/abs/2609.19124 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d102d43cbe27 (Metraipolis archive dc_d102d43cbe27, sha256 0ac31d3e01d487da1cba1e92f92fed70fd0204ca47f544ddd8dbb50b3161414c)
BibTeX
@misc{dcd102d43cbe27,
title = {Flag Game: A Toy Model for Mechanistic Swarm Interpretability — arXiv:2609.19124},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19124},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d102d43cbe27; sha256 0ac31d3e01d487da1cba1e92f92fed70fd0204ca47f544ddd8dbb50b3161414c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19124. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game, a toy model for studying the mechanisms of collective belief formation. Concretely, a hidden country flag defines the ground truth, and each bounded agent directly observes only a private crop but can exchange beliefs and weigh social evidence from peers. Despite its simplicity, the Flag Game reproduces rich collective phenomenology: non-monotonic scaling of performance with population size, accuracy gains from social-awareness prompting and team diversity, and strong effects of organizational structure. In particular, we identify that collective belief collapse at small population sizes turns into collective belief polarization as the population grows. This polarization causes the performance decline at large population sizes, but creates diversity in collective beliefs. Finally, we dissect the mechanisms underlying collective belief collapse and polarization with two complementary approaches. We first introduce social circuit attribution, a technique to predict which agent, and what view, matters most to collective dynamics, and verify its predictions by causal interventions on agents, tracing how agent patching changes collective outcomes. However, the efficacy of causal interventions on agents decreases as the population grows. We therefore develop a statistical mechanical theory for larger populations and verify that it matches the empirical phase diagram. Together, these results take a first step toward mechanistic swarm interpretability, a science of how the properties of individual agents and their communication give rise to emergent collective behavior. Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-17 in cond-mat.stat-mech). Categorie arXiv: Artificial Intelligence (cs.AI) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistical Mechanics (cond-mat.stat-mech); Multiagent Systems (cs.MA); Physics and Society (physics.soc-ph). Pagina del lavoro: https://arxiv.org/abs/2609.19124 — 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 2026-10-15T17:06:03.936Z dalla pagina https://arxiv.org/catchup/cond-mat.stat-mech/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).