{"paper_id":"2512.14744","title":"VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation","authors":["Adewale Akinfaderin","Shreyas Subramanian"],"paper_date":"2025-12-12","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2512.14744v1","page_url":"https://thequant.space/flowcharts/verafi-verified-agentic-financial-intelligence-through-neur/","scores":{"empirical_rigor":7,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes VERAFI, a neurosymbolic agentic framework that integrates retrieval, tool-use, and policy‑guided generation for verified financial intelligence.","quote":"This paper introduces VERAFI (Verified Agentic Financial Intelligence), an agentic framework with neurosymbolic policy generation for verified financial intelligence.","summary":"Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during reasoning, even with perfect retrieval. This paper introduces VERAFI (Verified…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"FinanceBench subset","provider":null,"kind":"benchmark","access":"public","period":null,"universe":"American Water Works (2015-2018), AMD (2022), American Express (2022), Boeing (2022)","quote":"we construct our evaluation dataset using a targeted subset of companies from FinanceBench (Islam et al. 2023) and ConvFinQA (Chen et al. 2022). Our dataset focuses on four major corporations: American Water Works (2015-2018 filings), AMD (2022 filings), American Express (2022 filings), and Boeing (2022 filings)."},{"name":"ConvFinQA","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"we construct our evaluation dataset using a targeted subset of companies from FinanceBench (Islam et al. 2023) and ConvFinQA (Chen et al. 2022)."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"VERAFI achieves 94.7% factual correctness and 96.4% completeness, an 81% relative improvement over traditional dense retrieval with reranking.","kind":"performance","quote":"Our best‑performing configuration, VERAFI with neurosymbolic validation, achieves 94.7% factual correctness and 96.4% completeness, substantially outperforming all baseline methods"},{"finding":"The neurosymbolic policy layer adds a 4.3 percentage‑point gain over the pure agentic baseline.","kind":"performance","quote":"The neurosymbolic policy layer alone contributes a 4.3 percentage point gain over pure agentic processing, specifically targeting persistent mathematical and logical errors."},{"finding":"Dense retrieval combined with cross‑encoder reranking (Dense+Rerank) attains 66.7% recall, the best retrieval performance among tested methods.","kind":"performance","quote":"Dense+Rerank achieves best performance, dominating across all metrics with 66.7% recall, successfully retrieving relevant documents for approximately two‑thirds of financial queries."},{"finding":"Agentic processing with web search raises factual correctness from 52.4% (Dense+Reranker) to 90.4% before neurosymbolic validation.","kind":"performance","quote":"factual correctness increasing from 52.4% (Dense + Reranker) to 90.4% with agentic processing and web search, and reaching 94.7% with neurosymbolic validation."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"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":"2026-11-14T17:19:11Z"},"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/"}