FinRiskAtlas is a Chinese-language benchmark designed to evaluate large language models (LLMs) for financial risk review by focusing on decision‑aligned tasks rather than generic financial knowledge. It contains 9,742 instances across 53 task families, including 42 domain‑knowledge families and 11 downstream review operations defined by explicit evaluation contracts. The extended FinRisk‑Ask framework replays 680 pre‑action states from 104 professional trajectories, withholding future evidence during inference to assess evidence‑state control and request targeting. Results across 33 model configurations show that operation‑level evaluation yields distinct rankings and that knowledge‑based shortlisting can incur significant regret, while frequent use of the Ask branch does not necessarily improve evidence acquisition, highlighting gaps in broad financial capability scores.
By Suyang Zhong, Jingzhe Zhu, Qi Xu, Liyao Sun, Yin Wang, Qingqing Sun, Shuai Chen, Tianyi Zhang
The paper proposes a three‑engine architecture for reliable financial AI, combining a financial knowledge graph, a deterministic optimization engine, and a multi‑agent LLM layer. A coordination layer called context engineering selects and validates query‑specific context from ERP systems and other tools. Observations from 15 deployments show that multi‑agent validation reduces hallucination rates to below 1%, while reusable mappings and templates cut deployment time from six to two weeks.
By Pradeep Kumar GS, Ravi Tanniru
arXiv:2607. 25877v1 Announce Type: new Abstract: This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focus on uncertainty quantification.
By Bart Custers, Koorosh Aslansefat
The paper proposes a three‑engine architecture for reliable financial AI, combining a financial knowledge graph, a deterministic optimization engine, and a multi‑agent LLM layer. A coordination layer called context engineering selects and validates context from ERP systems, tools, and tenants to ensure numerical accuracy, traceability, and auditability. Observations from 15 deployments show that graph‑backed multi‑agent validation can reduce hallucination rates from 7‑9% to below 1%, while reusable mappings and validation policies cut deployment time from six to two weeks.
arXiv:2607. 19409v1 Announce Type: new Abstract: Recent advances in large language models have accelerated deployment of agentic systems in operational finance.
By Wolfgang M. Pauli, Sarah Panda, Kidus Admassu, Said Bleik, Ademola Okerinde, Jeremy Reynolds
Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree.
The paper introduces a probabilistic framework that decomposes predictive uncertainty into three components: specification uncertainty, residual aleatoric uncertainty, and epistemic uncertainty. It shows that specification uncertainty quantifies the expected reduction in Bayes risk when missing intent is revealed, while residual aleatoric uncertainty represents the remaining risk after intent is known. Experiments across domains demonstrate that specification uncertainty best detects underspecified inputs, whereas residual aleatoric uncertainty best identifies in‑distribution prediction errors.
By Roman Vashurin, Mikhail Seleznyov, Assel Yermekova, Fedor Chernogorskii, Danila Zykov, Elena Tutubalina, Alexander Panchenko, Preslav Nakov, Nikita Kotelevskii, Maxim Panov
arXiv:2601.15322v3 Announce Type: replace-cross
Abstract: Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Ha...
By Raffi Khatchadourian
arXiv:2608.24842v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions....
By Miao Liu, Zhizhe Liu
arXiv:2605. 14355v3 Announce Type: replace Abstract: As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work.
By Xueqing Peng, Zhuohan Xie, Yupeng Cao, Haohang Li, Lingfei Qian, Yan Wang, Vincent Jim Zhang, Huan He, Xuguang Ai, Linhai Ma, Ruoyu Xiang, Yueru He, Yi Han, Shuyao Wang, Yuqing Guo, Mingyang Jiang, Yilun Zhao, Youzhong Dong, Xiaoyu Wang, Yankai Chen, Ye Yuan, Qiyuan Zhang, Fuyuan Lyu, Haolun Wu, Yonghan Yang, Zichen Zhao, Yuyang Dai, Fan Zhang, Rania Elbadry, Ayesha Gull, Muhammad Usman Safder, Nuo Chen, Fengbin Zhu, Tianshi Cai, Zimu Wang, Polydoros Giannouris, Yuechen Jiang, Zhiwei Liu, Mohsinul Kabir, Yuyan Wang, Yixiang Zheng, Yangyang Yu, Weijin Liu, Wenbo Cao, Anke Xu, Peng Lu, Jerry Huang, Mingquan Lin, Prayag Tiwari, Yijia Zhao, V\'ictor Guti\'errez-Basulto, Xiao-Yang Liu, Kaleb E Smith, Jiahuan Pei, Arman Cohan, Jimin Huang, Yuehua Tang, Alejandro Lopez-Lira, Xi Chen, Xue Liu, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou
arXiv:2608. 13706v1 Announce Type: cross Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text.
By Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain
AgenticFinBench is a new benchmark comprising 230 real‑world financial tasks across eight categories, two languages, and four complexity levels, designed to capture the breadth and open‑ended nature of financial AI work. It introduces a reference‑free evaluation framework that uses question‑specific rubrics and a two‑stage claim audit to detect hallucinations, aligning assessment more closely with real‑world financial practice. Experiments on 18 agent configurations show that ignoring hallucinations inflates performance, that harness differences drive evidence grounding more than model differences, and that task complexity reduces quality scores, highlighting challenges in explaining financial impacts and comparing data consistently.
By Shu Zhou, Ziyang He, Yuxin Rao, Yudong Fang, Jiali Qian, Dongyuan Chen, Juntao Zhang, Yong Hu