The study examined how different communication regimes affect a swarm of 200 trading agents from four model families over seven U.S. trading days. Groups that could communicate—via isolation, message boards, or shared notes—tended to hold more of the same stocks than isolated groups, and agents were more likely to reuse phrases seen in group posts. While seeing a groupmate’s post increased phrase reuse, it did not noticeably alter that morning’s trades, though communicating groups tended to sell in step more often than isolated ones.
By Avid Fayaz, Harry Zhang, H{\aa}vard Alstadheim, Erik Nordl\"of, Vilhelm Karlin, Andr\'e Silva
arXiv:2606. 03544v1 Announce Type: new Abstract: Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior.
By Linyue Pan, Yaoming Zhu, Lin Qiu, Xuezhi Cao, Xunliang Cai
arXiv:2610.20360v1 Announce Type: new
Abstract: Gossip, defined as evaluative talk about absent third parties, is widely seen as a uniquely human social practice. This study examines whether comparab...
By Yong-Hui Hua, Chih-Han Lin, Shu-Kai Hsieh
The Flag Game is a toy model designed to study how AI agents form collective beliefs. In the game, each agent sees only a private crop of a hidden country flag and can share beliefs with peers, leading to complex phenomena such as non‑monotonic performance scaling, accuracy gains from social awareness, and polarization that degrades performance at large population sizes. The authors introduce social circuit attribution to identify key agents and views, and develop a statistical mechanical theory to explain collective belief collapse and polarization in larger populations.
By Elizabeth Pavlova, Hidenori Tanaka
arXiv:2610.24833v1 Announce Type: cross
Abstract: As AI agents become increasingly connected through networks and take on tasks that require negotiation and joint decision-making, a systematic approa...
By Jin Gao
arXiv:2608. 16801v1 Announce Type: new Abstract: We study how teams of AI coding agents coordinate while solving programming tasks.
By Giuseppe Destefanis, Tomaso Aste
arXiv:2608. 16578v1 Announce Type: new Abstract: AI agents increasingly operate as part of interacting systems rather than in isolation.
By Batu El, Jinhee Paeng, Fatih Dinc, Shiye Su, Mete Erdogan, Aneesh Pappu, Haotian Ye, Wanjia Zhao, Surya Ganguli, James Zou
arXiv:2604. 20050v3 Announce Type: replace-cross Abstract: Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movements?
By Spyros Galanis
arXiv:2608.28399v2 Announce Type: replace
Abstract: In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This p...
By Yupeng Zhang, Liuyuan Jiang, Hongyi Huang, Bingheng Li, Lisha Chen
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 me...
arXiv:2609.07675v1 Announce Type: cross
Abstract: Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets,...
By Zelin Li, Yiyun Su, Matt White, Zhipeng Wang, Xiao-Yang Liu, Tianyu Shi
arXiv:2610.33011v1 Announce Type: cross
Abstract: While recent advances in autonomous agents enable them to coordinate on increasingly complex tasks, prior work shows that this growing capacity for c...
By Eric Onyame, Runtao Zhou, Kowshik Thopalli, Bhavya Kailkhura, Chirag Agarwal