FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived f

arXiv:2603.22305v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks including sentiment

arXiv:2608.11683v1 Announce Type: new Abstract: AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full

arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model

arXiv:2610.21074v1 Announce Type: new Abstract: Computational biologists increasingly delegate substantial analyses to AI agents in long-horizon, multi-turn sessions, yet most

arXiv:2608.18534v1 Announce Type: new Abstract: Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on

arXiv:2603.22744v1 Announce Type: new Abstract: Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or

arXiv:2608.00764v1 Announce Type: new Abstract: Financial indicators are essential tools for transforming raw financial data into interpretable measures for various downstream

arXiv:2603.24943v1 Announce Type: new Abstract: This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in solving real-world