From Natural Language to Executable Option Strategies via Large Language Models

2026-03-17

AI Summary

This work addresses the challenge of accurately translating natural language expressions of trading intent into executable options strategies, which requires complex reasoning over multidimensional options chain data under strict constraints. To this end, the authors propose a neuro-symbolic hybrid approach that introduces a domain-specific Options Query Language (OQL) as a structured intermediate representation. This OQL guides large language models in performing syntax-constrained semantic parsing, while a deterministic symbolic engine validates and executes the resulting strategies. By reframing free-form text generation as a controlled parsing task, the method achieves substantial improvements over direct generation baselines on a newly constructed options strategy dataset, demonstrating significant gains in both execution accuracy and logical consistency.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Neuro-Symbolic Learning
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Large Language Models (LLMs) excel at general code generation, yet translating natural-language trading intents into correct option strategies remains challenging. Real-world option design requires reasoning over massive, multi-dimensional option chain data with strict constraints, which often overwhelms direct generation methods. We introduce the Option Query Language (OQL), a domain-specific intermediate representation that abstracts option markets into high-level primitives under grammatical rules, enabling LLMs to function as reliable semantic parsers rather than free-form programmers. OQL queries are then validated and executed deterministically by an engine to instantiate executable strategies. We also present a new dataset for this task and demonstrate that our neuro-symbolic pipeline significantly improves execution accuracy and logical consistency over direct baselines.

Problem

• natural language to code
• option strategies
• executable trading intents
• option chain data
• semantic parsing

Innovation

• Option Query Language
• Large Language Models
• neuro-symbolic pipeline
• semantic parsing
• executable option strategies