智能体
arxiv.org ·
LLM 智能体社会中的金融脆弱性：协调失败与稳定机制
该 arXiv 预印本提出 FRAIL 受控实验框架，将 LLM 智能体置于银行挤兑、债务展期和奖励众筹三类动态金融环境中。在七款主流 LLM 上，77% 的基线银行挤兑场景和 83% 的债务展期场景以失败告终，且无智能体被指示破坏系统。作者比较补偿承诺、集中承诺协议和参与者主导联盟三种交互机制，发现三者均改善总体结果，但没有单一机制在所有金融结构下最优；成功稳定共享的时序特征是广泛承诺在防御行为自我强化前早期形成。研究强调单智能体能力不等于安全金融系统，系统级评估与交互设计是金融 AI 安全的核心问题，代码已公开。
AI推荐理由 arXiv 预印本，作者提出 FRAIL 受控实验框架，将 LLM 智能体置于银行挤兑、债务展期和奖励众筹三类动态金融环境中，测试七款主流 LLM。摘要给出具体量化结果：77% 的基线银行挤兑场景和 83% 的债务展期场景以失败告终，即使没有智能体被指示破坏系统；并比较补偿承诺、集中承诺协议和参与者主导联盟三种交互机制，发现没有单一机制在所有金融结构下最优，成功稳定共享的时序特征是广泛承诺在防御行为自我强化前早期形成。新信息在于把金融 AI 安全从单智能体层面提升到系统层面，并提供可复现代码。局限是预印本尚未经同行评审，实验为受控模拟，不能直接外推到真实金融市场。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.30940 (cs)
[Submitted on 25 Sep 2026]
Title:Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms
Authors:Zhenhao Fu, Ruipeng Xu, Qibing Ren
View a PDF of the paper titled Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms, by Zhenhao Fu and 2 other authors
View PDF
HTML (experimental)
Abstract:Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial decision-making, financial AI safety must therefore be considered not only at the level of individual agents, but also at the level of the systems they jointly create. We study this problem with FRAIL, a controlled experimental framework that places LLM agents in three dynamic financial environments---bank runs, debt rollover, and reward crowdfunding---where agents' decisions reshape the financial conditions faced by others. Across seven leading LLMs, we find widespread collective fragility even when no agent is instructed to destabilize the system: 77\% of baseline bank-run episodes and 83\% of debt-rollover episodes end in failure. We then compare three interaction mechanisms based on compensated commitments, centralized commitment agreements, and participant-led coalitions. All three improve aggregate outcomes, but no single mechanism performs best across all financial structures. Across mechanisms, successful stabilization shares a common temporal pattern: broad commitment forms early, before defensive behavior becomes self-reinforcing. Our findings show that individually capable agents do not automatically form safe financial systems, highlighting system-level evaluation and interaction design as central problems for financial AI safety. Code is available at this https URL.
Comments:
Subjects:
Artificial Intelligence (cs.AI); General Finance (q-fin.GN)
Cite as:
arXiv:2609.30940 [cs.AI]
(or
arXiv:2609.30940v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.30940
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zhenhao Fu [view email]
[v1]
Fri, 25 Sep 2026 07:55:14 UTC (4,012 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms, by Zhenhao Fu and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
q-fin
q-fin.GN
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?)