智能体
arxiv.org ·
超越代理架构：基于 LLM 的交易系统中的执行假设与可复现性
该 arXiv 论文（v2，2026-09-22 修订）对 LLM 与 agentic 系统用于金融交易的研究做主题综述与可复现性审计，用编码证据矩阵覆盖 30 项与交易相关的原始研究，评估时点控制、数据切分透明度、留出评估、成本与换手率处理、执行语义、标的范围定义及工件发布。作者指出，样本中架构报告普遍比判断交易结果是否具备经济可解释性或可复现性所需的评估假设更清晰；文中 10 只股票的示例仅作方法学脚手架，用以说明显式摩擦与择时选择会显著压缩主动策略结果。结论是 LLM 交易研究的下一步不只是更好的 agent 设计，还需在执行现实性、可复现性与评估可比性上建立更清晰的报告标准。
AI推荐理由 arXiv 预印本（v2，2026-09-22 修订），作者为 Junyi Yao、Zihao Zheng、Baichuan Li，属可验证的学术来源。核心新信息是对 30 项 LLM 交易相关原始研究做编码证据矩阵与可复现性审计，指出架构报告普遍比评估假设（时点控制、数据切分、执行时点、换手率与交易成本建模）更清晰，并给出 10 只股票的示例说明摩擦与择时假设会显著压缩主动策略结果。局限：这是综述与审计而非新模型或新系统，10-equity 示例仅为方法学脚手架，摘要未给出具体审计统计数字，结论为呼吁更清晰的执行现实性与可复现性报告标准。对做 LLM 金融 Agent 的开发者有方法论价值，但不构成可直接落地的技术突破。
72
正文
Computer Science > Artificial Intelligence
arXiv:2606.08285 (cs)
[Submitted on 6 Jun 2026 (v1), last revised 22 Sep 2026 (this version, v2)]
Title:Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems
Authors:Junyi Yao, Zihao Zheng, Baichuan Li
View a PDF of the paper titled Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems, by Junyi Yao and 2 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) and agentic systems are increasingly proposed for financial trading, yet their reported performance remains difficult to compare because studies vary in data provenance, temporal split discipline, execution timing, turnover treatment, and transaction-cost modeling. This article presents a targeted topical review and reproducibility audit of execution realism in LLM-based trading research. A coded evidence matrix covering 30 trade-relevant primary studies is used to assess point-in-time controls, split transparency, held-out evaluation, cost and turnover treatment, execution semantics, universe definition, and artifact release. Across the audited sample, architecture reporting is generally clearer than the evaluation assumptions needed to judge whether a trading result is economically interpretable or reproducible. A 10-equity worked example is included only as a methodological scaffold to illustrate how explicit friction and timing choices can materially compress active-strategy results. The main conclusion is that the next useful step for LLM trading research is not only better agent design, but also clearer reporting standards for execution realism, reproducibility, and evaluation comparability.
Subjects:
Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computational Finance (q-fin.CP); Trading and Market Microstructure (q-fin.TR)
Cite as:
arXiv:2606.08285 [cs.AI]
(or
arXiv:2606.08285v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.08285
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Junyi Yao [view email]
[v1]
Sat, 6 Jun 2026 18:14:29 UTC (84 KB)
[v2]
Tue, 22 Sep 2026 16:18:02 UTC (161 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems, by Junyi Yao and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-06
Change to browse by:
cs
cs.CE
q-fin
q-fin.CP
q-fin.TR
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)