FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness

Computer Science > Artificial Intelligence [Submitted on 16 Jun 2026] FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness Pianran Guo, Pengcheng Zhou, Yucheng Jian, Shuhua Chen Financial multimodal reasoning requires agents to coordinate numerical computation, retrieval, visual interpretation, and temporal grounding across heterogeneous evidence sources. Existing tool-augmented agents improve execution fidelity, yet remain largely stateless across episodes, repeatedly rediscovering reasoning strategies and failure patterns. In high-stakes financial settings, this leads to unreliable tool routing, noisy retrieval, and hallucination-prone reasoning. We present FinAcumen, a financial reasoning agent framework centered on selective experience memory for tool-augmented multimodal reasoning. FinAcumen accumulates financially grounded reasoning experience from prior trajectories, distilling successful strategies and failure-derived cautionary rules into a persistent memory bank. During inference, retrieved experiences condition reasoning only when semantic relevance exceeds a calibrated threshold, while irrelevant memory is explicitly suppressed through a fallback mechanism. A deterministic financial tool environment further grounds numerical computation, retrieval, visual decoding, and answer this http URL four financial multimodal reasoning benchmarks, FinAcumen consistently improves a frozen 8B vision-language model over finance-specialized models and approaches leading proprietary general-purpose models. Further analysis shows that selective experience activation improves reasoning reliability under retrieval uncertainty. Our code is anonymously available at this https URL Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.17642 [cs.AI]   (or arXiv:2606.17642v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.17642 Focus to learn more Submission history From: Pianran Guo [view email] [v1] Tue, 16 Jun 2026 08:00:30 UTC (1,323 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)