{"slug": "why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets", "title": "Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets", "summary": "A new arXiv paper (2609.04373v1) finds that improving the capability of large language models (LLMs) can degrade system-level outcomes in financial markets, as more capable models exhibit correlated behavior that creates a non-diversifiable risk floor. The authors, using an agent-based simulation with LLM traders, show that frontier LLMs' correlated behavior increases with capability, reducing market risk when shared reasoning is accurate but becoming a liability under common misinformation. This 'capability paradox' suggests that better individual models do not necessarily lead to better system-level outcomes.", "body_md": "arXiv:2609.04373v1 Announce Type: new \nAbstract: Large language models (LLMs) are being deployed at scale in consequential real-world systems, from financial markets to content moderation to hiring. We show that improving individual model capability can degrade rather than improve system-level outcomes. We hypothesize that shared training and architectures can lead more capable LLMs to behave more similarly, creating correlated actions that do not diversify away. We develop a general framework showing how this correlation creates a non-diversifiable risk floor and test its predictions in financial markets using an agent-based simulation with LLM traders of varying general-purpose capability. We find that: (1) frontier LLMs exhibit significantly correlated behavior that increases with capability; (2) when their shared reasoning is accurate, increasing agent participation reduces market-level risk; and (3) when agents share a common misinformation environment, the same correlated behavior becomes a liability. Together, these results identify a capability paradox: improving individual models does not necessarily produce better system-level outcomes. Whether the same dynamics arise in other domains is an open empirical question.", "url": "https://wpnews.pro/news/why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets", "canonical_source": "https://arxiv.org/abs/2609.04373", "published_at": "2026-09-07 04:00:00+00:00", "updated_at": "2026-09-07 04:28:22.154867+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-safety"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets", "markdown": "https://wpnews.pro/news/why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets.md", "text": "https://wpnews.pro/news/why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets.txt", "jsonld": "https://wpnews.pro/news/why-better-models-can-create-riskier-systems-evidence-from-llm-agents-in-markets.jsonld"}}