Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic protocol for auditing LLM reasoning without ground truth access. The key constraint is blindness: the auditor evaluates only whether derivation steps support conclusions, enabling detection of trace-output inconsistency and, when latent competence exists, its recovery. RAudit measures process quality via CRIT-based reasonableness scores and varies critique formulation to study how social framing affects model response. We prove bounded correction and $O(\log(1/ε))$ termination. Experiments on mathematical reasoning (CAP-GSM8K) and causal judgment (CausalL2) reveal four mechanisms explaining model unreliability: (1) Latent Competence Suppression, where models derive correct answers then overwrite them under social pressure; (2) The False Competence Trap, where weaker judges mask sycophancy that stronger judges expose; (3) The Complexity-Vulnerability Tradeoff, where causal tasks induce more than 10 times higher sycophancy than mathematical tasks; and (4) Iatrogenic Critique, where authoritative correction harms weaker models. These findings challenge assumptions that capability implies robustness and that stronger feedback yields better outputs.

翻译：推理时扩展会放大推理病理现象：谄媚性、阶梯塌缩与过早确定性。本文提出RAudit，一种无需访问真实值的LLM推理诊断审计协议。其核心约束在于盲式性：审计者仅评估推导步骤是否支持结论，从而能够检测轨迹输出不一致性，并在潜在能力存在时实现其恢复。RAudit通过基于CRIT的合理性评分衡量过程质量，并通过调整批判表述研究社会框架如何影响模型响应。我们证明了有界修正性及$O(\log(1/ε))$终止复杂度。在数学推理（CAP-GSM8K）与因果判断（CausalL2）任务上的实验揭示了模型不可靠性的四种机制：（1）潜在能力抑制：模型推导出正确答案后在社会压力下将其覆盖；（2）虚假能力陷阱：较弱评判者掩盖的谄媚行为会被较强评判者暴露；（3）复杂度-脆弱性权衡：因果任务引发的谄媚性比数学任务高10倍以上；（4）医源性批判：权威性修正反而损害较弱模型。这些发现挑战了“能力意味着鲁棒性”及“更强反馈产生更好输出”的固有假设。