Misinformation Propagation in Benign Multi-Agent Systems
It addresses the reliability of multi-agent LLM systems in high-stakes settings by analyzing misinformation propagation, but the findings are incremental as they confirm known vulnerabilities with a new injection method.
The paper studies how intent-based misinformation injected into benign single-agent and multi-agent LLM systems degrades performance, finding that misinformation persists in multi-agent debate but that debate reduces degradation compared to single-agent prompting, with robustness depending on group composition and decision protocol.
Multi-agent systems, in which multiple large language model agents solve problems through turn-based interaction, are increasingly deployed in high-stakes settings such as medical diagnosis, legal analysis, and forensic decision-making. Their reliability can be at risk when single agents reason from incorrect or misleading context, e.g., from tool calls, since errors may propagate through agent interactions. This work studies this risk by injecting intent-based misinformation into benign single-agent and multi-agent systems across reasoning, knowledge, and alignment tasks. We find that misinformation can degrade single-agent performance and persists across multi-agent debate, with agents often retaining answers introduced by misinformed peers. Nevertheless, multi-agent debate reduces the resulting performance degradation compared to single-agent prompting, especially when most agents are not exposed to misinformation. Robustness depends on group composition and decision protocol. Consensus can be more stable than voting under peer pressure, while majorities can often steer misinformed agents back toward correct answers. Our results show that misinformation robustness in multi-agent systems depends on the underlying model and also on how agents exchange information and aggregate decisions.