{"paper_id":"2611.24845","title":"Vibe-Trading: Towards Agent-Native Trading","authors":["Haozhe Wu","Zhonghang Li","Chao Huang"],"paper_date":"2026-11-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2611.24845","page_url":"https://thequant.space/flowcharts/vibe-trading-towards-agent-native-trading/","scores":{"empirical_rigor":6,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes Vibe‑Trading, an agent‑native trading framework and all‑in‑one workspace that unifies market research, data, strategy generation, backtesting, portfolio analysis, paper trading, multi‑agent collaboration, and optional broker execution.","quote":"We present Vibe-Trading, a comprehensive agent-native trading framework and all-in-one workspace for building, evaluating, and evolving agents for financial trading. It unifies market research, financial data, strategy generation, backtesting, portfolio analysis, paper trading, multi-agent collaboration, and optional broker execution.","summary":"Existing AI agents can retrieve information, call tools, run experiments, and produce multi-step outputs. Yet most are built around relatively static workflows and struggle to preserve reliable state as the environment changes. Financial trading makes this limitation especially consequential…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Backtests fix all inputs except the policy’s strategy logic, and each result stores its universe, period, price convention, capital and costs.","type":"data","stated":"explicit","quote":"The workspace therefore fixes everything in a backtest except the policy’s strategy logic σ: r = E \u0000σ; θ, D \u0001 . • Aligned inputs D. Every value carries the basis needed to interpret it: instrument, currency, units, price adjustment and the time it became available, such as the filing date of a fundamental.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic option‑pricing template (European call and put under Black‑Scholes)","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Option pricing values a European call and put under Black–Scholes with S = K = 100, T = 1, r = 0.05, σ = 0.2 and q = 0.","support":"full"},{"name":"Synthetic historical returns for VaR calculation","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Historical VaR computes the value-at-risk of ten fixed returns between −8% and 5% at confidence 0.8 and horizon 1, reported as a positive loss.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R4a","candidates":{"front_matter":"n/a","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A shared engine computes fills, costs, settlement, accounting and metrics for every strategy using market‑specific settlement, price‑band and fee rules; costs are stored with each result and verified by a hash manifest.","card_quote":"Information a source does not provide stays missing instead of being inferred. • Shared measurement E. One engine computes fills, costs, settlement, accounting and metrics for every strategy, with market-specific settlement, price-band and fee rules. Valuation and risk analytics follow the same principle and refuse to compute without their required inputs. • Recorded conditions θ.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"All 250 boundary cases passed (250/250) and all 812 subsystem checks passed (812/812), demonstrating that the workspace and harness maintain their intended invariants.","kind":"performance","quote":"e Backtest evidence 1 7 27 46 74 95 Test cases 0 100 200 Artifact verifier Runtime and records Authority and audit Data and factors Valuation Numerical grounding 21 83 126 137 193 252 Test cases (a) Boundary suites: 250/250 passed (b) Subsystem checks: 812/812 passed Figure 5: Regression cases per boundary suite and per subsystem.","support":"full"},{"finding":"Tool‑use trials produced correct Black‑Scholes call and put prices (10.45 and 5.57) and a VaR result of 0.04, confirming artifact‑level and delivery‑level success.","kind":"performance","quote":"A.2 Tool-Use Trials The pricing oracle evaluates the Black–Scholes formula through the error function, giv-ing call and put prices of 10.45 and 5.57. The VaR oracle sorts the returns [−.08, −.04, −.02, −.01, 0, .01, .02, .03, .04, .05] and takes the second observation without inter-polation, giving a positive loss of 0.04.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":6,"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":true,"code_url":"https://github.com/HKUDS/Vibe-Trading","note":null},"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":3,"extracted_at":"2026-11-19T11:36:35Z"},"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/"}