Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

ACL ARR 2026 January Submission8825 Authors

Keywords: Multi-agent Debate, LLM Sycophancy, Persona Control

Abstract:

Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to refine arguments and foster innovative thinking. LLMs' inherent sycophancy can collapse debates into premature consensus, potentially undermining the benefits of multi-agent debate. While prior studies focus on user-LLM sycophancy, the impact of inter-agent sycophancy in debate remains poorly understood.
To address this gap, we introduce the first operational framework that (1) proposes a formal definition of sycophancy specific to MADS, (2) develops new metrics to evaluate the agent sycophancy level and its impact on information exchange in MADS, and (3) systematically investigates how varying levels of sycophancy across agent roles (debaters and judges) affects outcomes in both decentralized and centralized debate frameworks. Our findings reveal that sycophancy consistently correlates with disagreement collapse and performance degradation in multi-agent debates, and controlling debaters' sycophancy as a tunable parameter produces measurable gains. Building on these findings, we propose actionable MADS design principles, effectively balancing productive disagreement with cooperation in agent interactions.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: multi-agent systems, agent communication, agent coordination and negotiation

Languages Studied: English

Submission Number: 8825