Multi-stage LLM pipelines that perform multi-agent debate, intrinsic self-correction, or retrieval-augmented verification exhibit puzzling aggregate behaviors: accuracy plateaus and reversals across rounds, non-replication of debate gains on contemporary frontier models, intrinsic self-correction degradation, and qualitative cross-provider divergence in debate dynamics. Downstream agent response can be operationalized as two coupled decisions: detection (whether to treat upstream content as authoritative) and conditional generation (what to produce if not). This decomposition yields four observable response regimes, of which detection-without-correction is the load-bearing failure mode. Across a nine-cell empirical grid spanning four model families, four benchmarks (GSM8K, MATH-500, GPQA-Diamond, AIME), and two methods (multi-agent debate, intrinsic self-correction), we find that the conditional miscorrection rate is consistently dominant (53-94% across cohorts) while detection rate varies contextually by more than an order of magnitude. The framework unifies the four phenomena above as signatures of a common mechanism and characterizes detection threshold as a stable model/protocol-level regularity that persists across methods at matched benchmark difficulty.

翻译：多阶段LLM流水线通过多智能体辩论、内在自修正或检索增强验证执行任务时，呈现出令人困惑的聚合行为：轮次间的准确率平台期与反转、前沿模型上辩论收益的不可复制性、内在自修正性能退化，以及跨模型提供商的辩论动态质性分歧。下游智能体响应可操作化为两个耦合决策：检测（是否将上游内容视为权威）与条件生成（若不接受则生成什么）。该分解产生四种可观测的响应模式，其中"无需修正的检测"是主要失效模式。在覆盖四个模型家族、四个基准测试（GSM8K、MATH-500、GPQA-Diamond、AIME）及两种方法（多智能体辩论、内在自修正）的九宫格实证网格中，我们发现条件性误修正率始终占主导地位（各队列53-94%），而检测率随上下文情境变化超过一个数量级。该框架将上述四种现象统一为共同机制的表征，并识别出检测阈值作为稳定的模型/协议级规律，该规律在匹配基准难度下跨方法持续存在。