Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring

2026-06-27

AI Summary

This work addresses the dual-edged nature of reasoning trace exchange in multi-agent AI systems, where sharing intermediate reasoning steps can both correct errors and inadvertently propagate inaccuracies, potentially steering correct answers toward incorrect ones. The authors propose a runtime monitoring framework in which multiple language models first answer multiple-choice questions independently, then exchange reasoning traces to revise their responses. This approach enables the first systematic quantification of the proportions of beneficial versus detrimental answer revisions and identifies key conditions under which error propagation occurs. Empirical evaluations across domains including cybersecurity, networking, and general knowledge demonstrate that multi-agent reasoning can enhance accuracy under specific conditions, while also delineating scenarios where it introduces significant risks.

Abstract

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.

Problem

• error propagation
• multi-agent AI
• reasoning exchange
• reliability
• runtime monitoring

Innovation

• runtime monitoring
• error propagation
• multi-agent AI
• reasoning trace exchange
• answer revision