FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation
Researchers have developed FinCom, a new multi-agent system designed for financial analysis that uses a Disagree-or-Commit (DoC) protocol. This framework aims to prevent sycophancy, where agents conform to peer reasoning rather than evidence, by structuring dissent into the decision-making process. FinCom employs a Supervisor and three specialist agents (Research, Quantitative, Risk) with role-specific tools, requiring explicit critique or commitment before a unified recommendation is made. Evaluations show DoC improves reasoning accuracy and risk awareness compared to consensus-seeking baselines. AI
IMPACT Introduces a novel protocol to improve the reliability and transparency of AI agents in financial decision-making.