The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms

As AI transitions toward multi-agent systems (MAS), research paradigms operate on the assumption that agent collaboration mirrors the ''Wisdom of the Crowd.'' We challenge this assumption by formalizing the Consensus Paradox, a phenomenon in which agentic swarms prioritize internal agreement over logical truth. Through 36 experiments with 12,804 trajectories across three benchmarks (GAIA, Multi-Challenge, and SWE-bench) and three state-of-the-art (SOTA) model families (Gemini 3.1 Pro, Claude Sonnet 4.6, and GPT-5.4), we derive and empirically validate the Inverse-Wisdom Law. In kinship-dominant swarms, adding agents increases the stability of erroneous trajectories rather than the probability of truth. The introduction of additional logical audits converges the system toward a Cascade Point where internal disagreement entropy hits zero while factual error hits unity. Across 12 family configurations of a three-agent chain, we establish the Architectural Tribalism Asymmetry as a reproducible inference-time property of the model family that synthesizes the final answer. We demonstrate that terminal swarm integrity is strictly gated by the synthesizer's receptive logic rather than aggregate agent quality. A homogeneous Gemini swarm reached this Cascade Point in $100%$ of Multi-Challenge trajectories. Even when the reviewing agent rejected a planted error in every trajectory, a Gemini synthesizer reinstated it $60.9%$ of the time. Conversely, with the first two agents held fixed, swapping only the synthesizer's model family cut terminal error from $91.7%$ to $23.6%$. We define the Tribalism Coefficient (τ) and the Sycophantic Weight (σ) as the primary determinants of swarm failure. Finally, we establish the Heterogeneity Mandate as a foundational safety requirement for resilient agentic architectures.