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

• URL: http://arxiv.org/abs/2604.16913v1
• Date: Sat, 18 Apr 2026 08:46:37 GMT
• Title: The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus
• Abstract summary: We introduce Sentinel-Bench, an 840-inference empirical framework executing a strict intra-model ablation on Qwen-3.5-9B.<n>System 1 achieved 100% adversarial robustness, 100% juridical consistency, and state finality in under 13 seconds.<n>System 2 reasoning introduced catastrophic instability, fundamentally driven by a 26.7% Reasoning Non-Convergence (cognitive collapse) rate.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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

Related papers

• Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation [0.0]
  Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks.<n>These frameworks are currently optimized in a way that heavily favors final output accuracy rather than stability of the process.<n>We introduce Knowledge-Grounded Counterfactual Reasoning (KG-CFR), a dual-stage architecture that enforces a strict separation of concerns between a private, retrieval-augmented planning buffer, and a public execution layer.
  arXiv  Detail & Related papers  (2026-06-09T06:43:18Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure [1.885184624108961]
  8 of 11 models suffer catastrophic metacognitive degradation under adversarial pressure.<n>We identify a "Compliance Trap"<n>Models with advanced reasoning capabilities exhibit the most severe absolute degradation.
  arXiv  Detail & Related papers  (2026-05-04T09:40:21Z)
• From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resilient Agentic AI [8.947753534117298]
  Agentic AI is crossing trust boundaries faster than current risk models can represent.<n>We propose a mechanism-to-magnitude pipeline for resilient agentic and embodied AI.<n>We show the framework on two contrasting scenarios a real-time warehouse robot and a governance-instrumented financial-services agent.
  arXiv  Detail & Related papers  (2026-04-28T23:40:24Z)
• Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning [2.0391237204597368]
  We present the Causal Multi-Agent Decision Framework (C-MADF) for autonomous cyber defense.<n>C-MADF integrates causal modeling with adversarial dual-policy control.<n>On the real-world CICIoT2023 dataset, C-MADF reduces the false-positive rate from 11.2%, 9.7%, and 8.4% in three cutting-edge literature baselines to 1.8%.
  arXiv  Detail & Related papers  (2026-04-06T05:40:43Z)
• Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents [0.0]
  Unconstrained tool-using agents must decide which information source to query and act on.<n>We propose the Triadic Cognitive Architecture (TCA), a decision-theoretic framework that formalizes these failure modes via cognitive friction.<n>We validate TCA in two controlled environments designed to isolate stopping quality, action selection under congestion, and temporal urgency.
  arXiv  Detail & Related papers  (2026-03-31T17:30:25Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing [9.271196825503417]
  Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound.<n>We present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate.<n>It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training.
  arXiv  Detail & Related papers  (2026-03-21T04:12:04Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• Optimistic TEE-Rollups: A Hybrid Architecture for Scalable and Verifiable Generative AI Inference on Blockchain [4.254924788681319]
  We introduce Optimistic TEE-Rollups (OTR), a hybrid verification protocol that harmonizes constraints.<n>OTR achieves 99% of the throughput of centralized baselines with a marginal cost overhead of $0.07 per query.
  arXiv  Detail & Related papers  (2025-12-23T09:16:41Z)
• The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks [51.468144272905135]
  Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks.<n>We provide a theoretical analysis targeting backdoor attacks, focusing on how sparse decision boundaries enable disproportionate model manipulation.<n>We propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties.
  arXiv  Detail & Related papers  (2025-12-11T08:09:07Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• Deliberative Reasoning Network: An Uncertainty-Driven Paradigm for Belief-Tracked Inference with Pretrained Language Models [7.095344389368656]
  Deliberative Reasoning Network (DRN) is a novel paradigm that reframes logical reasoning from probability to uncertainty minimization.<n>DRN achieves intrinsic interpretability by explicitly tracking belief states and quantifying uncertainty for competing hypotheses.<n>We position DRN as a foundational, verifiable System 2 reasoning component for building more trustworthy AI systems.
  arXiv  Detail & Related papers  (2025-08-06T11:33:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.