Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring
For developers of multi-agent AI systems, this work provides a framework to assess when reasoning exchange improves reliability versus when it propagates errors, though the findings are preliminary and domain-specific.
The paper studies error propagation in multi-agent AI systems where agents exchange reasoning traces and revise answers. Experiments across cybersecurity, networking, and general knowledge domains show that such communication can both improve and degrade accuracy, with the framework identifying conditions that lead to reliability gains or error propagation.
Multi-agent AI systems can improve answer selection by allowing different language models to exchange reasoning traces, revise initial predictions, and support a final decision. However, such communication may also introduce reliability risks: reasoning from one agent can correct another agent's mistake, but it can also mislead an agent that was initially correct. This paper studies reliable multi-agent AI communication through reasoning exchange and runtime answer revision. We develop a framework in which agents first answer multiple-choice questions independently, then share reasoning traces and revise their decisions. We conduct numerical experiments where we evaluate whether this process improves accuracy, produces more positive than negative answer transitions, and remains effective across domains such as cybersecurity, networking, and general knowledge. The results help identify when multi-agent reasoning improves reliability and when it may propagate errors.