跳到正文
arXiv cs.AI· Boming Yang, Yuquan Wang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo·· 4 小时前AI 评分36

谁该进入交易小组?面向 LLM 交易智能体的任务条件化角色选择

Who Should Be on the Panel? Task-Conditioned Persona Selection for LLM Trading Agents

AI 导读

arXiv 论文提出任务条件化角色选择方法,并实现 FinPanel——一个 LLM 多智能体交易系统,由招聘者根据每只股票的方向盲统计特征为其选出一组交易员角色,各自独立给出每日判断,再由管理者综合决策。

正文 · 原文

View PDF HTML (experimental)

Abstract:Multi-agent LLM systems are built by fixing a cast of roles and then designing how the cast coordinates. Which agents should make up the group for a given task is left to the designer, and the same cast is reused for every task. Financial trading makes the cost of that choice visible: stocks trade differently, and the trading styles suited to one need not suit another. We study task-conditioned persona selection, composing the group from the characteristics of the task it will face, and instantiate it with FinPanel, an LLM multi-agent trading system in which a recruiter selects a panel of named trader personas for each stock from a direction-blind statistical sketch of how the stock trades, each persona gives an independent daily call in its own style, and a manager commits the trade after reading the panel's arguments and their desk-kept, hierarchical track records. Because nothing is returned to the traders, the panel stays the panel that was selected, and it can trade a new stock from an empty record. On eight US stocks over the out-of-knowledge year 2025, against three prior LLM trading agents re-implemented in the same framework and against rule-based, predictive and reinforcement-learning baselines, the selected panel is ahead of a fixed panel of the same size and of the prior agents run as their papers prescribe, with a shallower drawdown than buy-and-hold on every stock; it keeps its performance with no warm-up and with no record at all, whereas the memory-augmented agents' returns swing with their warm-up; and neither more seats nor the manager's reading of the arguments substitutes for selecting the right ones. Who is in the group is a design decision to be made per task, before how the group coordinates.
Comments: Accepted at the AI4F workshop, ICAIF 2026. Code: this https URL
Subjects: Trading and Market Microstructure (q-fin.TR); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.18150 [q-fin.TR]
  (or arXiv:2611.18150v1 [q-fin.TR] for this version)
  https://doi.org/10.48550/arXiv.2611.18150

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Boming Yang [view email]
[v1] Fri, 13 Nov 2026 13:25:31 UTC (284 KB)

来源:arXiv cs.AI · arxiv.org