作者位次 #4/4ACL 2026Findings· Findings of ACL
From Tasks to Teams: A Risk-First Evaluation Framework for Multi-Agent LLM Systems in Finance
Zichen Chen · Jianda Chen · Jiaao Chen · Misha Sra
摘要
Current financial benchmarks prioritize large language models (LLMs) for task accuracy and portfolio returns, yet overlook risks arising from multi-agent cooperation, tool-sharing, and real-world financial actions. We introduce M-SAEA, a Multi-agent, Safety-Aware Evaluation Agent that audits LLM...