arXiv:2605. 27864v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction.
FinSkillBench is an evaluation suite that tests whether language model agents can use financial domain skills to solve investment management tasks across portfolio construction, risk management, and fundamental analysis. The benchmark contains 12 subtasks with 2,603 episodes, each providing point‑in‑time inputs, hidden ground truth, and a verifier. Experiments show that curated skill packages improve performance significantly, while self‑generated skills offer little benefit, indicating that reliable procedural skills are crucial for effective AI agents in this domain.
arXiv:2606. 01886v1 Announce Type: new Abstract: Financial AI agents often fail for a simple reason: they make users carry the complexity.
Demand for personalized financial advising is growing, but consistent advisor expertise is difficult to obtain, scale, and encode in LLM systems. Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations.
arXiv:2607. 04103v3 Announce Type: replace-cross Abstract: Generative artificial intelligence is moving from general-purpose experimentation toward specialized applications across banking, capital markets, insurance, payments, and wealth management.
arXiv:2606.29793v3 Announce Type: replace Abstract: Demand for personalized financial advice is growing, yet current LLM-based advisors often fail to provide consistent and specialized guidance.\ Sim...
arXiv:2607. 21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs.
arXiv:2606. 20041v1 Announce Type: cross Abstract: We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs.
arXiv:2607. 21268v1 Announce Type: cross Abstract: In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists.
arXiv:2607. 27853v2 Announce Type: replace-cross Abstract: Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products.
The paper introduces an agentic strategic asset allocation pipeline called the Self Driving Portfolio, where 44 specialized agents generate market assumptions, 21 competing methods construct portfolios, and agents critique and vote on each other's outputs. A researcher agent can propose new construction methods, while a meta agent evaluates past forecasts against realized returns and rewrites agent code and prompts to enhance future performance. The entire process is governed by an Investment Policy Statement, mirroring the document that guides human portfolio managers, thereby constraining and directing autonomous agents.
arXiv:2608. 05545v1 Announce Type: cross Abstract: Generative AI used as a capable servant has greatly accelerated intellectual work, but it also risks eroding human epistemic agency by encouraging uncritical acceptance of AI-generated reasoning.