FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation

2026-05-30

AI Summary

This work addresses the susceptibility of existing large language model–based multi-agent financial systems to flattery effects, which can precipitate premature consensus and neglect of critical evidence, thereby degrading decision quality. To mitigate this, the authors propose FinCom, a novel framework that treats dissent as a governance primitive and introduces a lightweight, prompt-only Disagree-or-Commit (DoC) protocol. This protocol compels agents to explicitly critique or commit to supporting others’ reasoning before consensus is reached, enhancing accountability, transparency, and cognitive robustness. The system employs three specialized ReAct agents—research, quantitative, and risk management—each equipped with role-specific tools and coordinated by a central overseer. Evaluated on 90 handcrafted tasks and the latest financial agent benchmark, FinCom significantly outperforms consensus-based baselines, demonstrating marked improvements in both reasoning accuracy and risk awareness.

Abstract

Multi-agent systems powered by large language models (LLMs) are increasingly used for financial analysis and decision support. However, existing coordination schemes, especially those emphasizing consensus or debate, are vulnerable to sycophancy: agents conform to peer reasoning instead of evidence, leading to premature agreement and degraded outcomes. We introduce FinCom (Financial Committee), a governed multi-agent framework and interactive system that operationalizes the Disagree-or-Commit (DoC) protocol to embed structured dissent into financial AI committees. A central Supervisor orchestrates three ReAct-enabled specialist agents: Research, Quantitative, and Risk. Each agent is equipped with role-specific tools for retrieval, computation, and stress testing. During deliberation, agents must either explicitly critique or commit to their peers' reasoning before converging on a unified recommendation. This demonstration showcases how FinCom supports committee-style financial analysis through coordinated multi-agent interaction, including structured report generation and interactive decision support. Evaluated across the most recent financial agent benchmark, in addition to 90 internal handcrafted financial tasks using an LLM-as-a-Judge protocol, DoC improves reasoning accuracy and risk awareness significantly over a consensus-seeking baseline on both an in-house and external evaluation set. By reframing disagreement as a governance primitive rather than noise, FinCom offers a lightweight, prompt-only recipe for improving accountability, transparency, and epistemic robustness in agentic financial systems.

Problem

• multi-agent systems
• sycophancy
• financial decision support
• consensus bias
• reasoning degradation

Innovation

• Disagree-or-Commit
• multi-agent system
• financial AI
• structured dissent
• LLM coordination