智能体RAG中的级联幻觉：用于检测和缓解的CHARM框架
Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
AI总结：
针对多步智能体RAG管道中早期错误传播并放大为最终错误输出的级联幻觉问题，提出CHARM框架，通过阶段级事实验证、跨阶段一致性跟踪、置信度传播监控和级联解析触发四个组件实现检测与缓解，在多个数据集上达到89.4%的级联检测率和82.1%的错误传播减少。
摘要：
多步智能体检索增强生成（RAG）管道在复杂推理任务中展现出显著能力，但仍然容易受到一类现有幻觉检测机制系统性遗漏的故障影响：级联幻觉，即在管道早期阶段引入的错误会通过连续推理步骤传播并放大，产生自信但事实不正确的最终输出。为解决这一漏洞，我们将级联幻觉形式化为智能体RAG系统中的一种独特故障模式，提出四种级联模式的分类法，并引入CHARM（级联幻觉感知解析与缓解），一种用于检测和中断多步推理管道中错误传播的架构框架。CHARM包含四个组件——阶段级事实验证、跨阶段一致性跟踪、置信度传播监控和级联解析触发——它们与标准智能体RAG管道并行运行，无需替换架构。我们在HotpotQA、MuSiQue、2WikiMultiHopQA以及一个自定义对抗数据集上，在LangChain智能体管道配置下评估CHARM，实现了89.4%的级联检测率、5.3%的假阳性率、每阶段平均215 ms ± 18 ms的延迟开销，以及82.1%的错误传播减少，而输出级检测器仅为18.5%。组件消融实验证实每个检测模块对整体级联覆盖都有显著贡献。CHARM与人在回路监督框架集成，为生产级智能体AI部署提供完整的可靠性和治理栈。
英文摘要：
Multi-step agentic retrieval-augmented generation (RAG) pipelines have demonstrated significant capability for complex reasoning tasks, yet remain vulnerable to a class of failure that existing hallucination detection mechanisms systematically miss: cascading hallucination, where errors introduced at early pipeline stages propagate and amplify across successive reasoning steps, producing confident but factually incorrect final outputs. To address this vulnerability, we formalize cascading hallucination as a distinct failure mode in agentic RAG systems, present a four-type taxonomy of cascade patterns, and introduce CHARM (Cascading Hallucination Aware Resolution and Mitigation), an architectural framework for detecting and interrupting error propagation in multi-step reasoning pipelines. CHARM comprises four components - stage-level fact verification, cross-stage consistency tracking, confidence propagation monitoring, and cascade resolution triggering - that operate alongside standard agentic RAG pipelines without requiring architectural replacement. We evaluate CHARM on HotpotQA, MuSiQue, 2WikiMultiHopQA, and a custom adversarial dataset across LangChain agentic pipeline configurations, achieving an 89.4% cascade detection rate with a 5.3% false positive rate and 215 ms +/- 18 ms average latency overhead per stage, achieving an error propagation reduction of 82.1%, compared to 18.5% for output-level detectors. Component ablations confirm that each detection module contributes meaningfully to overall cascade coverage. CHARM integrates with human-in-the-loop oversight frameworks to provide a complete reliability and governance stack for production agentic AI deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
