Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

Computer Science > Artificial Intelligence [Submitted on 3 Jun 2026] Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation Saroj Mishra 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. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR); Information Retrieval (cs.IR) Cite as: arXiv:2606.04435 [cs.AI]   (or arXiv:2606.04435v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.04435 Focus to learn more Submission history From: Saroj Mishra [view email] [v1] Wed, 3 Jun 2026 04:33:47 UTC (806 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL cs.CR cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)