Research

Paper

AI LLM March 17, 2026

From Natural Language to Executable Option Strategies via Large Language Models

Authors

Haochen Luo, Zhengzhao Lai, Junjie Xu, Yifan Li, Tang Pok Hin, Yuan Zhang, Chen Liu

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.

Metadata

arXiv ID: 2603.16434
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16434v1</id>\n    <title>From Natural Language to Executable Option Strategies via Large Language Models</title>\n    <updated>2026-03-17T12:14:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.16434v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16434v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='q-fin.TR'/>\n    <published>2026-03-17T12:14:47Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Haochen Luo</name>\n    </author>\n    <author>\n      <name>Zhengzhao Lai</name>\n    </author>\n    <author>\n      <name>Junjie Xu</name>\n    </author>\n    <author>\n      <name>Yifan Li</name>\n    </author>\n    <author>\n      <name>Tang Pok Hin</name>\n    </author>\n    <author>\n      <name>Yuan Zhang</name>\n    </author>\n    <author>\n      <name>Chen Liu</name>\n    </author>\n  </entry>"
}