← Back to all news
arXiv AI By Avid Fayaz, Harry Zhang, H{\aa}vard Alstadheim, Erik Nordl\"of, Vilhelm Karlin, Andr\'e Silva

Test-Time Communication in Trading Agent Swarms

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

Hugging Face Trending Papers
Oct 27

Test-Time Communication in Trading Agent Swarms

The paper investigates how communication affects trading agents that operate independently rather than as a coordinated team. Over seven trading days, 200 agents from four model families were grouped under five communication regimes, from isolation to shared message boards, and their reading logs were recorded before each decision. Results showed that in two model families, communicating groups held more of the same stocks than isolated groups, and a group’s return was largely driven by shared holdings; agents were more likely to reuse phrases from groupmates, and communicating groups tended to sell in step more often than isolated ones, though isolated groups also converged on similar stocks, indicating that herding assessments must compare against a no‑peer baseline.

agents
More like this →
arXiv AI
Sep 17

Flag Game: A Toy Model for Mechanistic Swarm Interpretability

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
llmsagentssafety
More like this →