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

arXiv 2604.27274 ↗First posted 30 Apr 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collaboration mirrors the "Wisdom of the Crowd". We challenge this assumption by formalizing the Consensus Paradox: a phenomenon where agentic swarms prioritize internal architectural agreement over external logical truth. Through a 36 experiments encompassing 12,804 trajectories across three state-of-the-art (SOTA) benchmarks (GAIA, Multi-Challenge, and SWE-bench), we prove the Inverse-Wisdom Law: in kinship-dominant swarms, adding logical agents increases the stability of erroneous trajectories rather than the probability of truth. The introduction of additional logical audits converges the system toward a Logic Saturation where internal entropy hits zero while factual error hits unity. By evaluating the interaction between the 3 preeminent SOTA models (Gemini 3.1 Pro, Claude Sonnet 4.6, and GPT-5.4), we establish the Architectural Tribalism Asymmetry as a mechanistic law of transformer weights. We demonstrate that terminal swarm integrity is strictly gated by the synthesizer's receptive logic, rather than aggregate agent quality. We define the Tribalism Coefficient and the Sycophantic Weight as the primary mechanistic determinants of swarm failure. Finally, we establish the Heterogeneity Mandate as a foundational safety requirement for resilient agentic architectures.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 19 of its 29 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

19 of 29 references.

Closest ancestors · 7

Same direction, newest first

Other references · 12

2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
2023GAIA: a benchmark for General AI Assistantscited by 1,084
2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
2024MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixturescited by 73
2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
2025Levels of Autonomy for AI Agentscited by 45
2025Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debatecited by 29
2024Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debatecited by 16
2025Hallucination Mitigation using Agentic AI Natural Language-Based Frameworkscited by 12
2025Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowdscited by 6
2026Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debatecited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way