Understanding Communication Failures in Multi-Agent LLM Systems

A new arXiv paper (2610.32060v1) presents a corpus-grounded taxonomy of communication failures in multi-agent LLM systems, built from 3,211 failed multi-round trajectories spanning medical QA, coding, finance, multi-hop reasoning, ethics, and embodied text tasks. The authors find failures are dominated by recovery/correction and consensus/decision problems rather than isolated first-round mistakes, with many emerging after agents first observe peer responses, including early convergence, ignored dissent, suppressed correct minority answers, and wrong framings preserved across rounds. The paper recommends stronger disagreement handling, evidence verification, minority-signal preservation, and recovery checks before finalization.

arXiv:2610.32060v1 Announce Type: new Abstract: Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy alone cannot explain. Agents may converge too early, ignore dissent, suppress correct minority answers, or preserve a wrong framing across rounds. We present a corpus-grounded taxonomy of communication failures, built from 3,211 failed multi-round trajectories across medical QA, coding, finance, multi-hop reasoning, ethics, and embodied text tasks. Using this taxonomy, we analyze failure distributions across datasets and system designs, round-level error dynamics, recovery hardness, majority transitions, minority-signal suppression, and self-reported confidence. We find that failures are dominated by recovery/correction and consensus/decision problems rather than isolated first-round mistakes, with many emerging after agents first observe peer responses. Based on these findings, we recommend stronger disagreement handling, evidence verification, minority-signal preservation, and recovery checks before finalization.