5 papers
Herculean: An Agentic Benchmark for Financial Intelligence
Xueqing Peng, Zhuohan Xie, Yupeng Cao +60
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…
MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval
Xin Zhang, Kailai Yang, Chenyue Li +4
Memory mechanism is a core component of LLM-based agents, enabling reasoning and knowledge discovery over long-horizon contexts. Existing agent memory systems are typically designe…
Ebisu: Benchmarking Large Language Models in Japanese Finance
Xueqing Peng, Ruoyu Xiang, Fan Zhang +9
Japanese finance combines agglutinative, head-final linguistic structure, mixed writing systems, and high-context communication norms that rely on indirect expression and implicit…
All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection
Yuechen Jiang, Zhiwei Liu, Yupeng Cao +10
We introduce RFC Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC Bench operates at the paragraph level and captures th…
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
Xueqing Peng, Lingfei Qian, Yan Wang +44
Real-world financial analysis involves information across multiple languages and modalities, from reports and news to scanned filings and meeting recordings. Yet most existing eval…