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

[Submitted on 16 Jun 2026 (v1), last revised 23 Aug 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract: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 available at this https URL.

Submission history

From: Pianran Guo [view email]
[v1] Tue, 16 Jun 2026 08:00:30 UTC (1,323 KB)
[v2] Mon, 22 Jun 2026 05:24:56 UTC (1,321 KB)
[v3] Sun, 23 Aug 2026 12:00:54 UTC (1,321 KB)