English

The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus

Artificial Intelligence 2026-04-21 v1 Computation and Language Cryptography and Security Distributed, Parallel, and Cluster Computing

Abstract

Decentralized Autonomous Organizations (DAOs) are inclined explore Small Language Models (SLMs) as edge-native constitutional firewalls to vet proposals and mitigate semantic social engineering. While scaling inference-time compute (System 2) enhances formal logic, its efficacy in highly adversarial, cryptoeconomic governance environments remains underexplored. To address this, we introduce Sentinel-Bench, an 840-inference empirical framework executing a strict intra-model ablation on Qwen-3.5-9B. By toggling latent reasoning across frozen weights, we isolate the impact of inference-time compute against an adversarial Optimism DAO dataset. Our findings reveal a severe compute-accuracy inversion. The autoregressive baseline (System 1) achieved 100% adversarial robustness, 100% juridical consistency, and state finality in under 13 seconds. Conversely, System 2 reasoning introduced catastrophic instability, fundamentally driven by a 26.7% Reasoning Non-Convergence (cognitive collapse) rate. This collapse degraded trial-to-trial consensus stability to 72.6% and imposed a 17x latency overhead, introducing critical vulnerabilities to Governance Extractable Value (GEV) and hardware centralization. While rare (1.5% of adversarial trials), we empirically captured "Reasoning-Induced Sycophancy," where the model generated significantly longer internal monologues (averaging 25,750 characters) to rationalize failing the adversarial trap. We conclude that for edge-native SLMs operating under Byzantine Fault Tolerance (BFT) constraints, System 1 parameterized intuition is structurally and economically superior to System 2 iterative deliberation for decentralized consensus. Code and Dataset: https://github.com/smarizvi110/sentinel-bench

Keywords

Cite

@article{arxiv.2604.16913,
  title  = {The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus},
  author = {Syed Muhammad Aqdas Rizvi},
  journal= {arXiv preprint arXiv:2604.16913},
  year   = {2026}
}

Comments

Working paper. 14 pages, 3 figures, 6 tables. Code and dataset: https://github.com/smarizvi110/sentinel-bench

R2 v1 2026-07-01T12:15:52.778Z