Metraipolis › archive › dc_f5855f3cf80d
SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes — arXiv:2609.19705
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19705
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:16:05.271Z
- SHA-256 of the archived text
ee3ce919e17f2f71568326be0f2c601e7c027cd59b796b8263a95a8cd297d8d6- Stable URL of this page
https://metraipolis.com/documento/dc_f5855f3cf80d
How to cite
SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes — arXiv:2609.19705 — arXiv (en), https://arxiv.org/abs/2609.19705 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5855f3cf80d (Metraipolis archive dc_f5855f3cf80d, sha256 ee3ce919e17f2f71568326be0f2c601e7c027cd59b796b8263a95a8cd297d8d6)
BibTeX
@misc{dcf5855f3cf80d,
title = {SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes — arXiv:2609.19705},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19705},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5855f3cf80d; sha256 ee3ce919e17f2f71568326be0f2c601e7c027cd59b796b8263a95a8cd297d8d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19705. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely domain-agnostic and overlook the distinctive, high-consequence attack surface such settings create. We examine this gap through financial trading agents, a representative case of high-stakes agentic security, where a single compromised agent has direct execution authority over real capital in an adversarial, reflexive market. To this end, we present FARSIGHT (Financial Agent Robustness and Security Investigation and Global Holistic Testing), a framework that performs scheme-level evaluation of financial LLM agents on two axes: robustness under market turbulence (including flash-crash-like scenarios), and security against three attack types: attacks on information sources, attacks on agents, and agent-as-attacker behaviors. Applying FARSIGHT to 15 representative academic schemes, we find that most overlook robustness and realistic adversarial threats: 80% fail at least one core robustness metric and 100% exhibit security vulnerabilities. These two failure modes are inseparable: a small misjudgment can cascade into a market-wide crash on its own, while an adversary can deliberately trigger the same collapse at minimal cost. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.MA). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.19705 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T03:03:51.717Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).