Intrinsic self-correction in Large Language Models (LLMs) frequently fails in open-ended reasoning tasks due to ``hallucination snowballing,'' a phenomenon in which models recursively justify early errors during free-text reflection. While structured feedback can mitigate this issue, existing approaches often rely on externally trained critics or symbolic tools, reducing agent autonomy. This study investigates whether enforcing structured reflection purely through Outlines-based constrained decoding can disrupt error propagation without additional training. Evaluating an 8-billion-parameter model (Qwen3-8B), we show that simply imposing structural constraints does not improve self-correction performance. Instead, it triggers a new failure mode termed ``structure snowballing.'' We find that the cognitive load required to satisfy strict formatting rules pushes the model into formatting traps. This observation helps explain why the agent achieves near-perfect superficial syntactic alignment yet fails to detect or resolve deeper semantic errors. These findings expose an ``alignment tax'' inherent to constrained decoding, highlighting a tension between structural granularity and internal model capacity in autonomous workflows. Code and raw logs are available in the GitHub repository: https://github.com/hongxuzhou/agentic_llm_structured_self_critique.

翻译：大型语言模型（LLM）的内在自纠正能力在开放式推理任务中常常失败，原因是“幻觉雪崩”现象——模型在自由文本反思过程中递归地合理化早期错误。虽然结构化反馈可以缓解这一问题，但现有方法通常依赖外部训练的评判者或符号工具，降低了智能体的自主性。本研究探讨是否仅通过基于Outlines的受限解码来强制实施结构化反思，就能在无需额外训练的情况下打断错误传播。通过评估一个80亿参数的模型（Qwen3-8B），我们表明，简单施加结构约束并不能提升自纠正性能。相反，它触发了一种新的失败模式，称为“结构雪崩”。我们发现，满足严格格式规则所需的认知负荷将模型推向格式陷阱。这一观察有助于解释为何智能体实现了近乎完美的表层句法对齐，却未能检测或解决更深层次的语义错误。这些发现揭示了受限解码固有的“对齐代价”，突显了自主工作流程中结构粒度与模型内部能力之间的紧张关系。代码和原始日志可在GitHub仓库获取：https://github.com/hongxuzhou/agentic_llm_structured_self_critique。