arXiv cs.MA· Avid Fayaz, Harry Zhang, H{\aa}vard Alstadheim, Erik Nordl\"of, Vilhelm Karlin, Andr\'e Silva·· 11 小时前AI 评分38
交易智能体集群中的测试时通信
Test-Time Communication in Trading Agent Swarms
AI 导读
研究用四个模型家族的 200 个交易智能体、每组十个，在五种通信机制下运行七个美股交易日，发现两个家族中通信组的持仓重合度远高于隔离组，且组收益主要来自成员共同持有的股票。看到同组帖子会使智能体复用其中八词短语的概率提高 7 个百分点，但未检测到对当日交易的明显影响。由于隔离组也会趋同，评估羊群效应需以无同伴基线衡量超额趋同。
正文
Abstract:Communication between agents has mostly been studied on tasks with a shared objective and fast, clear feedback. Trading has neither: each agent manages its own account, with decisions being scored by markets late and noisily. A trading swarm is thus a population of independent decision-makers rather than a team, for which convergence is a risk and not the goal. We ran 200 agents from four model families in groups of ten under five communication regimes, from isolation to message boards and shared notes, over seven US trading days (1 to 9 October 2026), logging everything each agent read before every decision. In two of the four families, communicating groups came to hold far more of the same stocks than the isolated group. A group's return was largely the return on what its members held in common. Seeing a post from a groupmate made an agent 7 percentage points more likely to reuse an eight-word phrase from it. Agents that started too close together to see each other's posts shared such a phrase in 14% of cases, the rate that common inputs produce. Seeing the post did not detectably change that morning's trades. Case studies traced the adoption of positions and decision rules over subsequent days, and communicating groups sold in step more often than isolated ones. Because isolated groups also converged on the same stocks, sometimes completely, assessments of herding need to measure excess convergence relative to a no-peer baseline.
| Comments: | 31 pages, 10 figures, 10 tables |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.37448 [cs.MA] |
| (or arXiv:2610.37448v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37448 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Avid Fayaz [view email]
[v1]
Tue, 27 Oct 2026 15:54:05 UTC (166 KB)
来源：arXiv cs.MA · arxiv.org