Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making

TL;DR

This paper introduces the Catfish Agent, a role-specialized LLM designed to challenge consensus in multi-agent clinical decision-making, thereby enhancing diagnostic reasoning and reducing premature agreement.

Contribution

The paper proposes a novel Catfish Agent that injects dissent in multi-agent LLM frameworks, with mechanisms for complexity-aware and tone-calibrated interventions to improve clinical reasoning.

Findings

Outperforms existing multi-agent frameworks and commercial models on medical benchmarks.

Effectively stimulates deeper reasoning and reduces premature consensus.

Improves diagnostic accuracy in complex medical cases.

Abstract

Large language models (LLMs) have demonstrated strong potential in clinical question answering, with recent multi-agent frameworks further improving diagnostic accuracy via collaborative reasoning. However, we identify a recurring issue of Silent Agreement, where agents prematurely converge on diagnoses without sufficient critical analysis, particularly in complex or ambiguous cases. We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement. Inspired by the ``catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning. We formulate two mechanisms to encourage effective and context-aware interventions: (i) a complexity-aware intervention that modulates agent engagement based on case difficulty, and (ii) a tone-calibrated intervention articulated to balance critique and collaboration. Evaluations on nine medical Q&A and three medical VQA benchmarks show that our approach consistently outperforms both single- and multi-agent LLMs frameworks, including leading commercial models such as GPT-4o and DeepSeek-R1.