Understanding Metacognition in Multi-Agent LLMs: Routing, Not Reasoning

Mafizur Rahman, Lijun Qian

Keywords: Multi-agent coordination, agentic reasoning, agentic interpretability, information routing

TL;DR: This paper shows that metacognition in multi-agent LLM systems mostly works by routing and compressing uncertainty, not by generating better reasoning.

Abstract: Multi-agent reasoning and metacognitive strategies are widely employed to enhance large language model (LLM) performance; however, the functional role of metacognition remains unclear. Most existing approaches implicitly treat metacognition as a mechanism for generating improved or more diverse reasoning. In this work, we argue that metacognition primarily acts as an information routing and compression mechanism rather than a generator of new reasoning content. We introduce MC-MAS, an inference-time framework that separates problem solving from metacognitive arbitration, where independent solvers propose candidate answers and a metacognitive arbiter critiques and consolidates these outputs. Using routing-centric metrics such as semantic novelty, entropy reduction, and overconfidence errors, we analyze information flow across four reasoning benchmarks and multiple model settings. Results show that MC-MAS yields limited novelty but consistently reduces uncertainty and overconfident errors, with accuracy gains that are modest and dataset-dependent. We also find that reliable improvements arise from structured arbitration rather than reflection or increased sampling alone.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 21