{"paper_id":"2609.33470","title":"LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs","authors":["Haochen Luo","Yifan Li","Binh Minh An","Xiaolong Luo","Zhengzhao Lai","Yuan Zhang","Chen Liu"],"paper_date":"2026-09-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2609.33470","page_url":"https://thequant.space/flowcharts/liveoption-evaluating-llm-agents-in-structured-option-trading-with-nonlinear/","scores":{"empirical_rigor":8,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes LiveOption, an evaluation framework for LLM-driven option trading agents.","quote":"We introduce LiveOption, an evaluation framework for LLM-based agents in option trading.","summary":"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…","strategy":"GPT-OSS-120B option overlay"},"assumptions":{"status":"available","items":[{"assumption":"Option markets provide a more realistic stress test requiring reasoning about volatility dynamics, tail risk, capital efficiency, and structured strategies.","type":"market","stated":"explicit","quote":"our central hypothesis is that option markets provide a more realistic and demanding stress test for financial agents than stock-only environments, as they require simultaneous reasoning about volatility dynamics, tail risk, capital efficiency, and the construction of structured strategies."},{"assumption":"The backtesting engine simulates realistic brokerage-style execution with margin enforcement and multi‑leg position management.","type":"execution","stated":"explicit","quote":"it incorporates a fully-featured backtesting engine that simulates realistic brokerage-style execution, including margin enforcement and multi-leg position management"},{"assumption":"Trading costs are modeled as option commission $0.65 per contract, stock commission $0.0005 per share, slippage 1.0 bp, and mid‑quote fills.","type":"execution","stated":"explicit","quote":"Option commission $0.65 per contract Stock commission $0.0005 per share Slippage 1.0 bp applied to fill price Bid–ask spread Mid-quote fills (0 bp explicit spread cost)"}]},"datasets":{"status":"available","items":[{"name":"Overlay underlyings","provider":null,"kind":"options","access":"unknown","period":"2025 fiscal year","universe":"QQQ, NVDA, AMD, GOOG, TSLA","quote":"The five overlay underlyings, QQQ, NVDA, AMD, GOOG, and TSLA, are chosen to span the regimes a single-name option overlay must be evaluated against."}],"known":[],"sample":{"start":"2025-01","end":"2025-12","market":"US equities (QQQ, NVDA, AMD, GOOG, TSLA)","asset_class":"options","frequency":"daily"},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Option commission $0.65 per contract, stock commission $0.0005 per share, slippage 1.0 bp, mid‑quote fills.","quote":"Option commission $0.65 per contract Stock commission $0.0005 per share Slippage 1.0 bp applied to fill price Bid–ask spread Mid-quote fills (0 bp explicit spread cost)","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Option commission $0.65 per contract, stock commission $0.0005 per share, slippage 1.0 bp, mid‑quote fills.","card_quote":"Option commission $0.65 per contract Stock commission $0.0005 per share Slippage 1.0 bp applied to fill price Bid–ask spread Mid-quote fills (0 bp explicit spread cost)","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Current LLM agents achieve negative episode returns across all tasks, with no statistically significant cross‑model differences.","kind":"negative","quote":"Our results reveal systematic limitations in current LLM agents: typical episode returns are negative in every task, no cross-model difference survives correction for multiple comparisons"}],"reported_performance":{"strategy":"GPT-OSS-120B option overlay","sharpe":1.011,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":5,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:04:33Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}