LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs

2026-09-27

AI Summary

This study addresses the oversight of existing large language model (LLM) financial evaluations regarding the nonlinear payoffs and decision-making complexity inherent in multi-leg options strategies. We propose LiveOption, a framework integrating LLMs, multi-agent systems, and reinforcement learning to simulate structured sequential decision-making under realistic constraints, encompassing portfolio overlay, event-driven, and intraday trading scenarios. Furthermore, we design a standardized interaction protocol and a hierarchical metric system to comprehensively evaluate agent capabilities across four dimensions: effectiveness, quality, risk, and outcome. Experimental results demonstrate that current agents struggle to achieve competitive returns. Accordingly, this work establishes a rigorous evaluation benchmark that transcends single-outcome metrics for assessing LLM-based agents in complex derivatives markets.

Abstract

Large language models (LLMs) and multi-agent systems (MAS) have shown promise in financial decision-making, yet existing evaluations focus on equity trading and primarily assess directional prediction, overlooking the structural complexity of derivative markets. Option trading introduces fundamentally different challenges, including nonlinear payoffs and multi-leg strategy construction, requiring structured decisions rather than simple directional bets. We introduce LiveOption, an evaluation framework for LLM-based agents in option trading. LiveOption formulates the problem as structured sequential decision-making under realistic execution and capital constraints, and provides a reproducible environment with standardized interaction protocols. The framework includes three task suites covering portfolio overlays, event-driven earnings trading, and 0DTE intraday trading. We further propose a hierarchical metric suite that evaluates action validity, decision quality, risk characteristics, and outcome-level performance. Experiments show that current agents often fail to achieve competitive returns in most scenarios. LiveOption offers a principled testbed for evaluating structured decision-making beyond outcome-based metrics.

Problem

• LLM agents
• option trading
• nonlinear payoffs
• structured decision-making
• evaluation framework

Innovation

• LLM Agents
• Option Trading
• Evaluation Framework
• Sequential Decision-Making
• Hierarchical Metrics